Spaces:
Sleeping
Sleeping
| { | |
| "generated_at": "2026-04-22T17:27:54.272678+00:00", | |
| "entries": [ | |
| { | |
| "task": "browse_comp", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-06T09-15-14+00-00_browse-comp_GDPC9YUBLV9YcBbXEXobtp.eval", | |
| "n_samples": 1266, | |
| "metrics": { | |
| "browse_comp_scorer/browse_comp_accuracy": 0.005529225908372828, | |
| "browse_comp_scorer/calibration_error": 0.6462085308056872 | |
| }, | |
| "primary_metric": "browse_comp_scorer/browse_comp_accuracy", | |
| "primary_value": 0.005529225908372828 | |
| }, | |
| { | |
| "task": "chembench", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-06T10-22-06+00-00_chembench_KCdkkLJrftkEFQAZCGZFes.eval", | |
| "n_samples": 2785, | |
| "metrics": { | |
| "chembench_scorer/analytical_chemistry": 0.2565789473684211, | |
| "chembench_scorer/chemical_preference": 0.521, | |
| "chembench_scorer/general_chemistry": 0.3959731543624161, | |
| "chembench_scorer/inorganic_chemistry": 0.532608695652174, | |
| "chembench_scorer/materials_science": 0.39759036144578314, | |
| "chembench_scorer/organic_chemistry": 0.47785547785547783, | |
| "chembench_scorer/physical_chemistry": 0.3090909090909091, | |
| "chembench_scorer/technical_chemistry": 0.525, | |
| "chembench_scorer/toxicity_and_safety": 0.29777777777777775, | |
| "chembench_scorer/all": 0.42333931777378814, | |
| "chembench_scorer/stderr": 0.009364182260674946 | |
| }, | |
| "primary_metric": "chembench_scorer/analytical_chemistry", | |
| "primary_value": 0.2565789473684211 | |
| }, | |
| { | |
| "task": "class_eval", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-06T10-26-06+00-00_class-eval_cGDFrjDfcbzG8noci3pjFy.eval", | |
| "n_samples": 100, | |
| "metrics": { | |
| "class_eval_scorer/mean": 0.82, | |
| "class_eval_scorer/std": 0.38612291966536916 | |
| }, | |
| "primary_metric": "class_eval_scorer/mean", | |
| "primary_value": 0.82 | |
| }, | |
| { | |
| "task": "coconot", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-06T10-36-47+00-00_coconot_FWbyEttT5diDPSP4QmoGcU.eval", | |
| "n_samples": 1001, | |
| "metrics": {}, | |
| "primary_metric": null, | |
| "primary_value": null | |
| }, | |
| { | |
| "task": "commonsense_qa", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-06T12-20-37+00-00_commonsense-qa_Usgh7g3socHuVp8YXaRwyU.eval", | |
| "n_samples": 1221, | |
| "metrics": { | |
| "choice/accuracy": 0.8206388206388207, | |
| "choice/stderr": 0.010983995312829072 | |
| }, | |
| "primary_metric": "choice/accuracy", | |
| "primary_value": 0.8206388206388207 | |
| }, | |
| { | |
| "task": "compute_eval", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-06T12-24-46+00-00_compute-eval_Edb4EceUjUL99wGTjuXZNu.eval", | |
| "n_samples": 406, | |
| "metrics": {}, | |
| "primary_metric": null, | |
| "primary_value": null | |
| }, | |
| { | |
| "task": "cybermetric_10000", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-06T12-25-37+00-00_cybermetric-10000_DDcNWjEeZEygrWHuHDdscx.eval", | |
| "n_samples": 10180, | |
| "metrics": { | |
| "choice/accuracy": 0.8370333988212181, | |
| "choice/stderr": 0.003660733726931372 | |
| }, | |
| "primary_metric": "choice/accuracy", | |
| "primary_value": 0.8370333988212181 | |
| }, | |
| { | |
| "task": "compute_eval", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-06T12-41-03+00-00_compute-eval_NqBwbQdRqz3remFSrxsYds.eval", | |
| "n_samples": 406, | |
| "metrics": {}, | |
| "primary_metric": null, | |
| "primary_value": null | |
| }, | |
| { | |
| "task": "drop", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-06T12-46-41+00-00_drop_Pu92XqwFr2nAzVzFG5UiLe.eval", | |
| "n_samples": 9535, | |
| "metrics": { | |
| "f1/mean": 0.7846345044572627, | |
| "f1/stderr": 0.00623405733968922 | |
| }, | |
| "primary_metric": "f1/mean", | |
| "primary_value": 0.7846345044572627 | |
| }, | |
| { | |
| "task": "DS-1000", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-06T14-37-16+00-00_DS-1000_HgwFC7QMc9BcDp65eaDsNx.eval", | |
| "n_samples": 1000, | |
| "metrics": { | |
| "ds1000_scorer/accuracy": 0.29, | |
| "ds1000_scorer/stderr": 0.01435639599990562 | |
| }, | |
| "primary_metric": "ds1000_scorer/accuracy", | |
| "primary_value": 0.29 | |
| }, | |
| { | |
| "task": "frontier_cs", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-06T16-55-02+00-00_frontier-cs_ibS7TvePU2ZmmnKf76Yssq.eval", | |
| "n_samples": 211, | |
| "metrics": {}, | |
| "primary_metric": null, | |
| "primary_value": null | |
| }, | |
| { | |
| "task": "frontierscience", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-06T18-11-26+00-00_frontierscience_oJrfV4pA3xYvweDmwKYv72.eval", | |
| "n_samples": 160, | |
| "metrics": {}, | |
| "primary_metric": null, | |
| "primary_value": null | |
| }, | |
| { | |
| "task": "gpqa_diamond", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-06T18-18-38+00-00_gpqa-diamond_j3v7ThvDrwSvBsiPB9EjEy.eval", | |
| "n_samples": 198, | |
| "metrics": { | |
| "choice/accuracy": 0.37373737373737376, | |
| "choice/stderr": 0.02548983505458481 | |
| }, | |
| "primary_metric": "choice/accuracy", | |
| "primary_value": 0.37373737373737376 | |
| }, | |
| { | |
| "task": "gsm8k", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-06T19-02-02+00-00_gsm8k_MajdJnCuQ8wofq9gej2JT5.eval", | |
| "n_samples": 1319, | |
| "metrics": { | |
| "match/accuracy": 0.8658074298711145, | |
| "match/stderr": 0.009388953419897707 | |
| }, | |
| "primary_metric": "match/accuracy", | |
| "primary_value": 0.8658074298711145 | |
| }, | |
| { | |
| "task": "healthbench", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-06T19-50-16+00-00_healthbench_MvfYGKWi88PWRBVjEu9DNP.eval", | |
| "n_samples": 5000, | |
| "metrics": {}, | |
| "primary_metric": null, | |
| "primary_value": null | |
| }, | |
| { | |
| "task": "healthbench", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-06T19-58-36+00-00_healthbench_b4sTzUWTPmP4YPARB7U4BD.eval", | |
| "n_samples": 5000, | |
| "metrics": {}, | |
| "primary_metric": null, | |
| "primary_value": null | |
| }, | |
| { | |
| "task": "healthbench", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-06T19-59-53+00-00_healthbench_WwMmzC8WM6SFcU7KShoEjx.eval", | |
| "n_samples": 5000, | |
| "metrics": {}, | |
| "primary_metric": null, | |
| "primary_value": null | |
| }, | |
| { | |
| "task": "hellaswag", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-06T20-01-27+00-00_hellaswag_BCovoA4VKpUb5WxVFidEaG.eval", | |
| "n_samples": 10042, | |
| "metrics": { | |
| "choice/accuracy": 0.8494323839872535, | |
| "choice/stderr": 0.0035689602471017175 | |
| }, | |
| "primary_metric": "choice/accuracy", | |
| "primary_value": 0.8494323839872535 | |
| }, | |
| { | |
| "task": "hle", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-06T20-08-25+00-00_hle_BoQTuGNwy5oUD47sTmHq8M.eval", | |
| "n_samples": 2500, | |
| "metrics": {}, | |
| "primary_metric": null, | |
| "primary_value": null | |
| }, | |
| { | |
| "task": "humaneval", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-06T20-10-26+00-00_humaneval_kgbP88K9xWJui3po5kirkF.eval", | |
| "n_samples": 164, | |
| "metrics": { | |
| "verify/accuracy": 0.7378048780487805, | |
| "verify/stderr": 0.034450002891734555 | |
| }, | |
| "primary_metric": "verify/accuracy", | |
| "primary_value": 0.7378048780487805 | |
| }, | |
| { | |
| "task": "ifeval", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-06T20-18-35+00-00_ifeval_P3xLhBCeJLeQArParpPTt4.eval", | |
| "n_samples": 541, | |
| "metrics": { | |
| "instruction_following/prompt_strict_acc": 0.7005545286506469, | |
| "instruction_following/prompt_strict_stderr": 0.01970983402967294, | |
| "instruction_following/prompt_loose_acc": 0.7264325323475046, | |
| "instruction_following/prompt_loose_stderr": 0.019183727107392842, | |
| "instruction_following/inst_strict_acc": 0.7817745803357314, | |
| "instruction_following/inst_strict_stderr": 0.01434183633895034, | |
| "instruction_following/inst_loose_acc": 0.8081534772182254, | |
| "instruction_following/inst_loose_stderr": 0.01318783401832037, | |
| "instruction_following/final_acc": 0.754228779638027, | |
| "instruction_following/final_stderr": 0.018893789976485772 | |
| }, | |
| "primary_metric": "instruction_following/prompt_strict_acc", | |
| "primary_value": 0.7005545286506469 | |
| }, | |
| { | |
| "task": "ifevalcode", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-06T20-34-24+00-00_ifevalcode_Vyr6koRns4e24VfN3teqWD.eval", | |
| "n_samples": 810, | |
| "metrics": { | |
| "_ifevalcode_scorer/overall_accuracy": 0.043209876543209874, | |
| "_ifevalcode_scorer/correctness": 0.14814814814814814, | |
| "_ifevalcode_scorer/instruction_adherence": 0.19382716049382717, | |
| "_ifevalcode_scorer/cpp_correctness": 0.03, | |
| "_ifevalcode_scorer/csharp_correctness": 0.04854368932038835, | |
| "_ifevalcode_scorer/java_correctness": 0.11764705882352941, | |
| "_ifevalcode_scorer/javascript_correctness": 0.24, | |
| "_ifevalcode_scorer/php_correctness": 0.19, | |
| "_ifevalcode_scorer/python_correctness": 0.3142857142857143, | |
| "_ifevalcode_scorer/shell_correctness": 0.12, | |
| "_ifevalcode_scorer/typescript_correctness": 0.12, | |
| "_ifevalcode_scorer/cpp_instruction": 0.06, | |
| "_ifevalcode_scorer/csharp_instruction": 0.02912621359223301, | |
| "_ifevalcode_scorer/java_instruction": 0.058823529411764705, | |
| "_ifevalcode_scorer/javascript_instruction": 0.27, | |
| "_ifevalcode_scorer/php_instruction": 0.21, | |
| "_ifevalcode_scorer/python_instruction": 0.3142857142857143, | |
| "_ifevalcode_scorer/shell_instruction": 0.35, | |
| "_ifevalcode_scorer/typescript_instruction": 0.26 | |
| }, | |
| "primary_metric": "_ifevalcode_scorer/overall_accuracy", | |
| "primary_value": 0.043209876543209874 | |
| }, | |
| { | |
| "task": "ifeval", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-09T13-18-19+00-00_ifeval_MvZPWnCXKkneoMWs8JtsMc.eval", | |
| "n_samples": 541, | |
| "metrics": { | |
| "instruction_following/prompt_strict_acc": 0.6950092421441775, | |
| "instruction_following/prompt_strict_stderr": 0.019812612681224306, | |
| "instruction_following/prompt_loose_acc": 0.7171903881700554, | |
| "instruction_following/prompt_loose_stderr": 0.019380609595892707, | |
| "instruction_following/inst_strict_acc": 0.7745803357314148, | |
| "instruction_following/inst_strict_stderr": 0.014481047789338244, | |
| "instruction_following/inst_loose_acc": 0.7973621103117506, | |
| "instruction_following/inst_loose_stderr": 0.013611377047300163, | |
| "instruction_following/final_acc": 0.7460355190893496, | |
| "instruction_following/final_stderr": 0.019117794541837867 | |
| }, | |
| "primary_metric": "instruction_following/prompt_strict_acc", | |
| "primary_value": 0.6950092421441775 | |
| }, | |
| { | |
| "task": "ifeval", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-09T13-52-01+00-00_ifeval_Z6fqctaBepFTjHUnYTuga9.eval", | |
| "n_samples": 541, | |
| "metrics": { | |
| "instruction_following/prompt_strict_acc": 0.7208872458410351, | |
| "instruction_following/prompt_strict_stderr": 0.01930308095849728, | |
| "instruction_following/prompt_loose_acc": 0.7486136783733827, | |
| "instruction_following/prompt_loose_stderr": 0.018668216152240437, | |
| "instruction_following/inst_strict_acc": 0.7985611510791367, | |
| "instruction_following/inst_strict_stderr": 0.013898041448111482, | |
| "instruction_following/inst_loose_acc": 0.8213429256594724, | |
| "instruction_following/inst_loose_stderr": 0.013067598352473049, | |
| "instruction_following/final_acc": 0.7723512502382568, | |
| "instruction_following/final_stderr": 0.018624484902237608 | |
| }, | |
| "primary_metric": "instruction_following/prompt_strict_acc", | |
| "primary_value": 0.7208872458410351 | |
| }, | |
| { | |
| "task": "compute_eval", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-10T17-17-50+00-00_compute-eval_6xfRTrQeR8QEsYS7ZzTbFP.eval", | |
| "n_samples": 406, | |
| "metrics": { | |
| "correctness_scorer/accuracy": 0.15763546798029557, | |
| "correctness_scorer/stderr": 0.018107124797491256 | |
| }, | |
| "primary_metric": "correctness_scorer/accuracy", | |
| "primary_value": 0.15763546798029557 | |
| }, | |
| { | |
| "task": "ifevalcode", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-10T17-57-58+00-00_ifevalcode_2SFicRVnr83kAbE4j6zQNc.eval", | |
| "n_samples": 810, | |
| "metrics": { | |
| "_ifevalcode_scorer/overall_accuracy": 0.04814814814814815, | |
| "_ifevalcode_scorer/correctness": 0.16419753086419753, | |
| "_ifevalcode_scorer/instruction_adherence": 0.19135802469135801, | |
| "_ifevalcode_scorer/cpp_correctness": 0.03, | |
| "_ifevalcode_scorer/csharp_correctness": 0.019417475728155338, | |
| "_ifevalcode_scorer/java_correctness": 0.09803921568627451, | |
| "_ifevalcode_scorer/javascript_correctness": 0.3, | |
| "_ifevalcode_scorer/php_correctness": 0.22, | |
| "_ifevalcode_scorer/python_correctness": 0.3333333333333333, | |
| "_ifevalcode_scorer/shell_correctness": 0.15, | |
| "_ifevalcode_scorer/typescript_correctness": 0.16, | |
| "_ifevalcode_scorer/cpp_instruction": 0.05, | |
| "_ifevalcode_scorer/csharp_instruction": 0.02912621359223301, | |
| "_ifevalcode_scorer/java_instruction": 0.058823529411764705, | |
| "_ifevalcode_scorer/javascript_instruction": 0.3, | |
| "_ifevalcode_scorer/php_instruction": 0.22, | |
| "_ifevalcode_scorer/python_instruction": 0.26666666666666666, | |
| "_ifevalcode_scorer/shell_instruction": 0.37, | |
| "_ifevalcode_scorer/typescript_instruction": 0.24 | |
| }, | |
| "primary_metric": "_ifevalcode_scorer/overall_accuracy", | |
| "primary_value": 0.04814814814814815 | |
| }, | |
| { | |
| "task": "lab_bench_litqa", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-10T18-57-37+00-00_lab-bench-litqa_hKGCZmd5JMLjfUkKDYzHV2.eval", | |
| "n_samples": 199, | |
| "metrics": { | |
| "precision_choice/accuracy": 0.1457286432160804, | |
| "precision_choice/precision": 0.31868131868131866, | |
| "precision_choice/coverage": 0.457286432160804, | |
| "precision_choice/stderr": 0.025074817920573277 | |
| }, | |
| "primary_metric": "precision_choice/accuracy", | |
| "primary_value": 0.1457286432160804 | |
| }, | |
| { | |
| "task": "lab_bench_suppqa", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-10T18-57-58+00-00_lab-bench-suppqa_XQ2iPVhfG8VctMGYFVfRx9.eval", | |
| "n_samples": 82, | |
| "metrics": { | |
| "precision_choice/accuracy": 0.036585365853658534, | |
| "precision_choice/precision": 0.3333333333333333, | |
| "precision_choice/coverage": 0.10975609756097561, | |
| "precision_choice/stderr": 0.020860168453036114 | |
| }, | |
| "primary_metric": "precision_choice/accuracy", | |
| "primary_value": 0.036585365853658534 | |
| }, | |
| { | |
| "task": "lab_bench_dbqa", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-10T18-58-45+00-00_lab-bench-dbqa_n9mDktMkUUF8dTpcJvYaLd.eval", | |
| "n_samples": 520, | |
| "metrics": { | |
| "precision_choice/accuracy": 0.026923076923076925, | |
| "precision_choice/precision": 0.45161290322580644, | |
| "precision_choice/coverage": 0.05961538461538462, | |
| "precision_choice/stderr": 0.007104806488908629 | |
| }, | |
| "primary_metric": "precision_choice/accuracy", | |
| "primary_value": 0.026923076923076925 | |
| }, | |
| { | |
| "task": "lab_bench_protocolqa", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-10T19-00-16+00-00_lab-bench-protocolqa_jjaEeMEKjU8y3eJq9JpvDz.eval", | |
| "n_samples": 108, | |
| "metrics": { | |
| "precision_choice/accuracy": 0.3333333333333333, | |
| "precision_choice/precision": 0.5373134328358209, | |
| "precision_choice/coverage": 0.6203703703703703, | |
| "precision_choice/stderr": 0.04557239513497755 | |
| }, | |
| "primary_metric": "precision_choice/accuracy", | |
| "primary_value": 0.3333333333333333 | |
| }, | |
| { | |
| "task": "lab_bench_seqqa", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-10T19-00-53+00-00_lab-bench-seqqa_YfdrQUgQYEwiFgri4nrccP.eval", | |
| "n_samples": 600, | |
| "metrics": { | |
| "precision_choice/accuracy": 0.30833333333333335, | |
| "precision_choice/precision": 0.42045454545454547, | |
| "precision_choice/coverage": 0.7333333333333333, | |
| "precision_choice/stderr": 0.018868842134251208 | |
| }, | |
| "primary_metric": "precision_choice/accuracy", | |
| "primary_value": 0.30833333333333335 | |
| }, | |
| { | |
| "task": "lab_bench_litqa", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-10T19-06-39+00-00_lab-bench-litqa_A5kfMMxb8PR3BVnKbvXnpX.eval", | |
| "n_samples": 199, | |
| "metrics": { | |
| "precision_choice/accuracy": 0.21105527638190955, | |
| "precision_choice/precision": 0.45652173913043476, | |
| "precision_choice/coverage": 0.4623115577889447, | |
| "precision_choice/stderr": 0.028999385807956583 | |
| }, | |
| "primary_metric": "precision_choice/accuracy", | |
| "primary_value": 0.21105527638190955 | |
| }, | |
| { | |
| "task": "lab_bench_dbqa", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-10T19-07-15+00-00_lab-bench-dbqa_ijzdCyeAiVkMamBPHaAiZ7.eval", | |
| "n_samples": 520, | |
| "metrics": { | |
| "precision_choice/accuracy": 0.01730769230769231, | |
| "precision_choice/precision": 0.2647058823529412, | |
| "precision_choice/coverage": 0.06538461538461539, | |
| "precision_choice/stderr": 0.0057245938837831726 | |
| }, | |
| "primary_metric": "precision_choice/accuracy", | |
| "primary_value": 0.01730769230769231 | |
| }, | |
| { | |
| "task": "lab_bench_protocolqa", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-10T19-08-49+00-00_lab-bench-protocolqa_6uUY6egQb6CnTNdmBQS6ry.eval", | |
| "n_samples": 108, | |
| "metrics": { | |
| "precision_choice/accuracy": 0.23148148148148148, | |
| "precision_choice/precision": 0.3968253968253968, | |
| "precision_choice/coverage": 0.5833333333333334, | |
| "precision_choice/stderr": 0.0407749470925263 | |
| }, | |
| "primary_metric": "precision_choice/accuracy", | |
| "primary_value": 0.23148148148148148 | |
| }, | |
| { | |
| "task": "lab_bench_seqqa", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-10T19-09-28+00-00_lab-bench-seqqa_dFhwiBeWSjpPY8kLXa7Fwp.eval", | |
| "n_samples": 600, | |
| "metrics": { | |
| "precision_choice/accuracy": 0.3333333333333333, | |
| "precision_choice/precision": 0.4424778761061947, | |
| "precision_choice/coverage": 0.7533333333333333, | |
| "precision_choice/stderr": 0.019261066555232926 | |
| }, | |
| "primary_metric": "precision_choice/accuracy", | |
| "primary_value": 0.3333333333333333 | |
| }, | |
| { | |
| "task": "lab_bench_litqa", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-10T19-13-22+00-00_lab-bench-litqa_a8K3WE2dzGLHJJiJRm2AWu.eval", | |
| "n_samples": 199, | |
| "metrics": { | |
| "precision_choice/accuracy": 0.1708542713567839, | |
| "precision_choice/precision": 0.3617021276595745, | |
| "precision_choice/coverage": 0.4723618090452261, | |
| "precision_choice/stderr": 0.026748273739817943 | |
| }, | |
| "primary_metric": "precision_choice/accuracy", | |
| "primary_value": 0.1708542713567839 | |
| }, | |
| { | |
| "task": "lab_bench_protocolqa", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-10T19-14-36+00-00_lab-bench-protocolqa_2kqiQqbAfppWGEUotjUVNu.eval", | |
| "n_samples": 108, | |
| "metrics": { | |
| "precision_choice/accuracy": 0.28703703703703703, | |
| "precision_choice/precision": 0.4696969696969697, | |
| "precision_choice/coverage": 0.6111111111111112, | |
| "precision_choice/stderr": 0.04373313040914761 | |
| }, | |
| "primary_metric": "precision_choice/accuracy", | |
| "primary_value": 0.28703703703703703 | |
| }, | |
| { | |
| "task": "lab_bench_seqqa", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-10T19-15-17+00-00_lab-bench-seqqa_RXGmnqK73nbrzDh9zHPWvW.eval", | |
| "n_samples": 600, | |
| "metrics": { | |
| "precision_choice/accuracy": 0.33, | |
| "precision_choice/precision": 0.4449438202247191, | |
| "precision_choice/coverage": 0.7416666666666667, | |
| "precision_choice/stderr": 0.019212370805984473 | |
| }, | |
| "primary_metric": "precision_choice/accuracy", | |
| "primary_value": 0.33 | |
| }, | |
| { | |
| "task": "lab_bench_cloning_scenarios", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-10T19-18-04+00-00_lab-bench-cloning-scenarios_Zq3u78LxcFxJyiCSSKZvK4.eval", | |
| "n_samples": 33, | |
| "metrics": { | |
| "precision_choice/accuracy": 0.15151515151515152, | |
| "precision_choice/precision": 0.2777777777777778, | |
| "precision_choice/coverage": 0.5454545454545454, | |
| "precision_choice/stderr": 0.06338333534349057 | |
| }, | |
| "primary_metric": "precision_choice/accuracy", | |
| "primary_value": 0.15151515151515152 | |
| }, | |
| { | |
| "task": "lingoly", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-10T19-25-25+00-00_lingoly_LeP6pqmJjYEwQkTVbgn79k.eval", | |
| "n_samples": 408, | |
| "metrics": { | |
| "exact_match_lingoly/no_context_delta": 0.0794351279788173, | |
| "exact_match_lingoly/no_context_mean": 0.06266548984995587, | |
| "exact_match_lingoly/full_context_mean": 0.14210061782877317 | |
| }, | |
| "primary_metric": "exact_match_lingoly/no_context_delta", | |
| "primary_value": 0.0794351279788173 | |
| }, | |
| { | |
| "task": "gaia", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-10T19-44-16+00-00_gaia_3YSjPWtq5SEWKngZZAAGVL.eval", | |
| "n_samples": 165, | |
| "metrics": { | |
| "gaia_scorer/accuracy": 0.05454545454545454, | |
| "gaia_scorer/stderr": 0.017732815098121694 | |
| }, | |
| "primary_metric": "gaia_scorer/accuracy", | |
| "primary_value": 0.05454545454545454 | |
| }, | |
| { | |
| "task": "mbpp", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-10T21-05-30+00-00_mbpp_QnZuB2zs8inFDFJP3YzHVJ.eval", | |
| "n_samples": 257, | |
| "metrics": { | |
| "verify/accuracy": 0.7898832684824902, | |
| "verify/stderr": 0.025461957733387858 | |
| }, | |
| "primary_metric": "verify/accuracy", | |
| "primary_value": 0.753307392996109 | |
| }, | |
| { | |
| "task": "medqa", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-10T21-13-11+00-00_medqa_AKJBXc9wHeWx4VZSrzryKo.eval", | |
| "n_samples": 1273, | |
| "metrics": { | |
| "choice/accuracy": 0.5066771406127258, | |
| "choice/stderr": 0.01401805371747913 | |
| }, | |
| "primary_metric": "choice/accuracy", | |
| "primary_value": 0.5066771406127258 | |
| }, | |
| { | |
| "task": "mind2web", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-10T21-20-17+00-00_mind2web_mB4eb9XM2RQ7TQp6zpvnn7.eval", | |
| "n_samples": 4060, | |
| "metrics": { | |
| "mind2web_scorer/element_accuracy": 0.3896551724137931, | |
| "mind2web_scorer/action_f1": 0.6475280616225271, | |
| "mind2web_scorer/step_success_rate": 0.30344827586206896, | |
| "mind2web_scorer/task_success_rate": 0.023054755043227664 | |
| }, | |
| "primary_metric": "mind2web_scorer/element_accuracy", | |
| "primary_value": 0.3896551724137931 | |
| }, | |
| { | |
| "task": "mind2web_sc", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-10T21-54-01+00-00_mind2web-sc_UBKJ76XH8nZeSNrwnGbfPS.eval", | |
| "n_samples": 10, | |
| "metrics": { | |
| "guard_agent_scorer/accuracy": 0.5, | |
| "guard_agent_scorer/Shopping": 0.75, | |
| "guard_agent_scorer/Travel": 0.4, | |
| "guard_agent_scorer/Entertainment": 0.0, | |
| "guard_agent_scorer/all": 0.5 | |
| }, | |
| "primary_metric": "guard_agent_scorer/accuracy", | |
| "primary_value": 0.5 | |
| }, | |
| { | |
| "task": "musr", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-10T22-00-14+00-00_musr_R6NEEeGwdVYxHkH3uqVAZk.eval", | |
| "n_samples": 250, | |
| "metrics": { | |
| "choice/accuracy": 0.54, | |
| "choice/stderr": 0.031584653891499004 | |
| }, | |
| "primary_metric": "choice/accuracy", | |
| "primary_value": 0.54 | |
| }, | |
| { | |
| "task": "niah", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-10T22-36-37+00-00_niah_3VckY2TjSXKysKB6vduAqo.eval", | |
| "n_samples": 225, | |
| "metrics": { | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_10000_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_position_0_accuracy": 5.266666666666667, | |
| "custom_model_graded_qa_with_history_scorer/target_position_7_accuracy": 3.8, | |
| "custom_model_graded_qa_with_history_scorer/target_position_14_accuracy": 3.8, | |
| "custom_model_graded_qa_with_history_scorer/target_position_21_accuracy": 3.933333333333333, | |
| "custom_model_graded_qa_with_history_scorer/target_position_28_accuracy": 4.066666666666666, | |
| "custom_model_graded_qa_with_history_scorer/target_position_35_accuracy": 4.066666666666666, | |
| "custom_model_graded_qa_with_history_scorer/target_position_42_accuracy": 3.933333333333333, | |
| "custom_model_graded_qa_with_history_scorer/target_position_50_accuracy": 4.066666666666666, | |
| "custom_model_graded_qa_with_history_scorer/target_position_57_accuracy": 4.2, | |
| "custom_model_graded_qa_with_history_scorer/target_position_64_accuracy": 4.733333333333333, | |
| "custom_model_graded_qa_with_history_scorer/target_position_71_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_position_78_accuracy": 5.133333333333334, | |
| "custom_model_graded_qa_with_history_scorer/target_position_85_accuracy": 4.6, | |
| "custom_model_graded_qa_with_history_scorer/target_position_92_accuracy": 4.733333333333333, | |
| "custom_model_graded_qa_with_history_scorer/target_position_100_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_17857_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_25714_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_33571_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_41428_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_49285_accuracy": 5.333333333333333, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_57142_accuracy": 5.2, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_65000_accuracy": 5.333333333333333, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_72857_accuracy": 4.466666666666667, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_80714_accuracy": 4.666666666666667, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_88571_accuracy": 3.6666666666666665, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_96428_accuracy": 3.533333333333333, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_104285_accuracy": 3.533333333333333, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_112142_accuracy": 3.4, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_120000_accuracy": 2.2, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_10000_target_position_0_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_10000_target_position_7_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_10000_target_position_14_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_10000_target_position_21_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_10000_target_position_28_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_10000_target_position_35_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_10000_target_position_42_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_10000_target_position_50_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_10000_target_position_57_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_10000_target_position_64_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_10000_target_position_71_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_10000_target_position_78_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_10000_target_position_85_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_10000_target_position_92_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_10000_target_position_100_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_17857_target_position_0_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_17857_target_position_7_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_17857_target_position_14_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_17857_target_position_21_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_17857_target_position_28_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_17857_target_position_35_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_17857_target_position_42_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_17857_target_position_50_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_17857_target_position_57_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_17857_target_position_64_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_17857_target_position_71_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_17857_target_position_78_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_17857_target_position_85_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_17857_target_position_92_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_17857_target_position_100_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_25714_target_position_0_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_25714_target_position_7_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_25714_target_position_14_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_25714_target_position_21_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_25714_target_position_28_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_25714_target_position_35_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_25714_target_position_42_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_25714_target_position_50_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_25714_target_position_57_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_25714_target_position_64_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_25714_target_position_71_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_25714_target_position_78_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_25714_target_position_85_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_25714_target_position_92_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_25714_target_position_100_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_33571_target_position_0_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_33571_target_position_7_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_33571_target_position_14_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_33571_target_position_21_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_33571_target_position_28_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_33571_target_position_35_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_33571_target_position_42_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_33571_target_position_50_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_33571_target_position_57_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_33571_target_position_64_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_33571_target_position_71_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_33571_target_position_78_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_33571_target_position_85_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_33571_target_position_92_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_33571_target_position_100_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_41428_target_position_0_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_41428_target_position_7_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_41428_target_position_14_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_41428_target_position_21_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_41428_target_position_28_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_41428_target_position_35_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_41428_target_position_42_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_41428_target_position_50_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_41428_target_position_57_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_41428_target_position_64_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_41428_target_position_71_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_41428_target_position_78_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_41428_target_position_85_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_41428_target_position_92_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_41428_target_position_100_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_49285_target_position_0_accuracy": 10.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_49285_target_position_7_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_49285_target_position_14_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_49285_target_position_21_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_49285_target_position_28_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_49285_target_position_35_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_49285_target_position_42_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_49285_target_position_50_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_49285_target_position_57_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_49285_target_position_64_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_49285_target_position_71_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_49285_target_position_78_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_49285_target_position_85_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_49285_target_position_92_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_49285_target_position_100_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_57142_target_position_0_accuracy": 10.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_57142_target_position_7_accuracy": 1.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_57142_target_position_14_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_57142_target_position_21_accuracy": 7.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_57142_target_position_28_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_57142_target_position_35_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_57142_target_position_42_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_57142_target_position_50_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_57142_target_position_57_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_57142_target_position_64_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_57142_target_position_71_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_57142_target_position_78_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_57142_target_position_85_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_57142_target_position_92_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_57142_target_position_100_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_65000_target_position_0_accuracy": 10.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_65000_target_position_7_accuracy": 7.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_65000_target_position_14_accuracy": 3.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_65000_target_position_21_accuracy": 3.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_65000_target_position_28_accuracy": 7.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_65000_target_position_35_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_65000_target_position_42_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_65000_target_position_50_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_65000_target_position_57_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_65000_target_position_64_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_65000_target_position_71_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_65000_target_position_78_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_65000_target_position_85_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_65000_target_position_92_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_65000_target_position_100_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_72857_target_position_0_accuracy": 3.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_72857_target_position_7_accuracy": 3.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_72857_target_position_14_accuracy": 3.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_72857_target_position_21_accuracy": 3.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_72857_target_position_28_accuracy": 3.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_72857_target_position_35_accuracy": 7.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_72857_target_position_42_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_72857_target_position_50_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_72857_target_position_57_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_72857_target_position_64_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_72857_target_position_71_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_72857_target_position_78_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_72857_target_position_85_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_72857_target_position_92_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_72857_target_position_100_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_80714_target_position_0_accuracy": 10.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_80714_target_position_7_accuracy": 3.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_80714_target_position_14_accuracy": 3.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_80714_target_position_21_accuracy": 3.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_80714_target_position_28_accuracy": 3.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_80714_target_position_35_accuracy": 3.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_80714_target_position_42_accuracy": 3.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_80714_target_position_50_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_80714_target_position_57_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_80714_target_position_64_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_80714_target_position_71_accuracy": 7.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_80714_target_position_78_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_80714_target_position_85_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_80714_target_position_92_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_80714_target_position_100_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_88571_target_position_0_accuracy": 3.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_88571_target_position_7_accuracy": 3.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_88571_target_position_14_accuracy": 3.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_88571_target_position_21_accuracy": 3.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_88571_target_position_28_accuracy": 3.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_88571_target_position_35_accuracy": 3.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_88571_target_position_42_accuracy": 3.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_88571_target_position_50_accuracy": 3.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_88571_target_position_57_accuracy": 1.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_88571_target_position_64_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_88571_target_position_71_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_88571_target_position_78_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_88571_target_position_85_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_88571_target_position_92_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_88571_target_position_100_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_96428_target_position_0_accuracy": 3.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_96428_target_position_7_accuracy": 1.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_96428_target_position_14_accuracy": 3.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_96428_target_position_21_accuracy": 3.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_96428_target_position_28_accuracy": 3.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_96428_target_position_35_accuracy": 3.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_96428_target_position_42_accuracy": 1.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_96428_target_position_50_accuracy": 1.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_96428_target_position_57_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_96428_target_position_64_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_96428_target_position_71_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_96428_target_position_78_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_96428_target_position_85_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_96428_target_position_92_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_96428_target_position_100_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_104285_target_position_0_accuracy": 1.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_104285_target_position_7_accuracy": 3.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_104285_target_position_14_accuracy": 3.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_104285_target_position_21_accuracy": 3.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_104285_target_position_28_accuracy": 3.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_104285_target_position_35_accuracy": 1.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_104285_target_position_42_accuracy": 3.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_104285_target_position_50_accuracy": 3.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_104285_target_position_57_accuracy": 1.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_104285_target_position_64_accuracy": 7.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_104285_target_position_71_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_104285_target_position_78_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_104285_target_position_85_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_104285_target_position_92_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_104285_target_position_100_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_112142_target_position_0_accuracy": 3.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_112142_target_position_7_accuracy": 3.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_112142_target_position_14_accuracy": 3.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_112142_target_position_21_accuracy": 3.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_112142_target_position_28_accuracy": 3.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_112142_target_position_35_accuracy": 3.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_112142_target_position_42_accuracy": 1.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_112142_target_position_50_accuracy": 3.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_112142_target_position_57_accuracy": 3.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_112142_target_position_64_accuracy": 3.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_112142_target_position_71_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_112142_target_position_78_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_112142_target_position_85_accuracy": 3.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_112142_target_position_92_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_112142_target_position_100_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_120000_target_position_0_accuracy": 1.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_120000_target_position_7_accuracy": 3.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_120000_target_position_14_accuracy": 1.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_120000_target_position_21_accuracy": 1.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_120000_target_position_28_accuracy": 1.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_120000_target_position_35_accuracy": 1.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_120000_target_position_42_accuracy": 3.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_120000_target_position_50_accuracy": 1.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_120000_target_position_57_accuracy": 3.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_120000_target_position_64_accuracy": 1.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_120000_target_position_71_accuracy": 3.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_120000_target_position_78_accuracy": 7.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_120000_target_position_85_accuracy": 1.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_120000_target_position_92_accuracy": 1.0, | |
| "custom_model_graded_qa_with_history_scorer/target_context_length_120000_target_position_100_accuracy": 5.0, | |
| "custom_model_graded_qa_with_history_scorer/overall_accuracy": 4.4222222222222225 | |
| }, | |
| "primary_metric": "custom_model_graded_qa_with_history_scorer/target_context_length_10000_accuracy", | |
| "primary_value": 5.0 | |
| }, | |
| { | |
| "task": "onet_m6", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-10T23-05-37+00-00_onet-m6_HoftZmjMT5rt6TRMwXcWwQ.eval", | |
| "n_samples": 397, | |
| "metrics": { | |
| "choice/accuracy": 0.45843828715365237, | |
| "choice/stderr": 0.025038991009441725 | |
| }, | |
| "primary_metric": "choice/accuracy", | |
| "primary_value": 0.45843828715365237 | |
| }, | |
| { | |
| "task": "paws", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-10T23-13-34+00-00_paws_XjCeQSsw4pkWThRSYmVDQ6.eval", | |
| "n_samples": 8000, | |
| "metrics": { | |
| "includes/accuracy": 0.849125, | |
| "includes/stderr": 0.004001995601318688 | |
| }, | |
| "primary_metric": "includes/accuracy", | |
| "primary_value": 0.849125 | |
| }, | |
| { | |
| "task": "personality_BFI", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-10T23-20-43+00-00_personality-BFI_m4T7FRaa7B2NVpjHWa9Jnq.eval", | |
| "n_samples": 44, | |
| "metrics": { | |
| "any_choice/Extraversion": 0.725, | |
| "any_choice/Agreeableness": 0.9777777777777777, | |
| "any_choice/Conscientiousness": 0.9777777777777777, | |
| "any_choice/Neuroticism": 0.325, | |
| "any_choice/Openness": 0.96 | |
| }, | |
| "primary_metric": "any_choice/Extraversion", | |
| "primary_value": 0.725 | |
| }, | |
| { | |
| "task": "personality_TRAIT", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-10T23-22-43+00-00_personality-TRAIT_CgNDCk9XqAC8echcJ8nzM8.eval", | |
| "n_samples": 8000, | |
| "metrics": { | |
| "any_choice/Openness": 0.5955955955955956, | |
| "any_choice/Conscientiousness": 0.7807807807807807, | |
| "any_choice/Extraversion": 0.381, | |
| "any_choice/Agreeableness": 0.7849246231155779, | |
| "any_choice/Neuroticism": 0.23423423423423423, | |
| "any_choice/Machiavellianism": 0.249, | |
| "any_choice/Narcissism": 0.143, | |
| "any_choice/Psychopathy": 0.016 | |
| }, | |
| "primary_metric": "any_choice/Openness", | |
| "primary_value": 0.5955955955955956 | |
| }, | |
| { | |
| "task": "piqa", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-10T23-31-10+00-00_piqa_ZSmkfNZ2QzD4VMfWMVLXrT.eval", | |
| "n_samples": 1838, | |
| "metrics": { | |
| "choice/accuracy": 0.8558215451577802, | |
| "choice/stderr": 0.008195721894805212 | |
| }, | |
| "primary_metric": "choice/accuracy", | |
| "primary_value": 0.8558215451577802 | |
| }, | |
| { | |
| "task": "pre_flight", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-10T23-33-53+00-00_pre-flight_8y3wJG4vAo9BQaAwGePq92.eval", | |
| "n_samples": 300, | |
| "metrics": { | |
| "choice/accuracy": 0.65, | |
| "choice/stderr": 0.02758386421836852 | |
| }, | |
| "primary_metric": "choice/accuracy", | |
| "primary_value": 0.65 | |
| }, | |
| { | |
| "task": "pubmedqa", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-10T23-34-40+00-00_pubmedqa_EvhwJR7W24QfLR7v9eZibJ.eval", | |
| "n_samples": 500, | |
| "metrics": { | |
| "choice/accuracy": 0.648, | |
| "choice/stderr": 0.021380042385946048 | |
| }, | |
| "primary_metric": "choice/accuracy", | |
| "primary_value": 0.648 | |
| }, | |
| { | |
| "task": "race_h", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-10T23-38-05+00-00_race-h_3vWCZyrUseBwe5yXK63qey.eval", | |
| "n_samples": 3498, | |
| "metrics": { | |
| "choice/accuracy": 0.8138936535162951, | |
| "choice/stderr": 0.006837259968738816 | |
| }, | |
| "primary_metric": "choice/accuracy", | |
| "primary_value": 0.8138936535162951 | |
| }, | |
| { | |
| "task": "sad_stages_full", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-10T23-44-42+00-00_sad-stages-full_aKc9U7kKry6sNR9qEeHrNf.eval", | |
| "n_samples": 800, | |
| "metrics": { | |
| "lenient_mcq_choice/accuracy": 0.33375, | |
| "lenient_mcq_choice/stderr": 0.016682297374225847 | |
| }, | |
| "primary_metric": "lenient_mcq_choice/accuracy", | |
| "primary_value": 0.33375 | |
| }, | |
| { | |
| "task": "sad_stages_oversight", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-10T23-45-49+00-00_sad-stages-oversight_jvAULJuEesC5q4DV8RxysE.eval", | |
| "n_samples": 400, | |
| "metrics": { | |
| "lenient_mcq_choice/accuracy": 0.50125, | |
| "lenient_mcq_choice/stderr": 0.02499992167907531 | |
| }, | |
| "primary_metric": "lenient_mcq_choice/accuracy", | |
| "primary_value": 0.50125 | |
| }, | |
| { | |
| "task": "sad_influence", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-10T23-46-28+00-00_sad-influence_TJBzA35GXboCABrCQgb5wM.eval", | |
| "n_samples": 255, | |
| "metrics": { | |
| "lenient_mcq_choice/accuracy": 0.5647058823529412, | |
| "lenient_mcq_choice/stderr": 0.03110897462660272 | |
| }, | |
| "primary_metric": "lenient_mcq_choice/accuracy", | |
| "primary_value": 0.5647058823529412 | |
| }, | |
| { | |
| "task": "sad_facts_llms", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-10T23-46-51+00-00_sad-facts-llms_YDCaoJtJ6z58VV3gKHvRVr.eval", | |
| "n_samples": 249, | |
| "metrics": { | |
| "lenient_mcq_choice/accuracy": 0.8032128514056225, | |
| "lenient_mcq_choice/stderr": 0.02508485073399091 | |
| }, | |
| "primary_metric": "lenient_mcq_choice/accuracy", | |
| "primary_value": 0.8032128514056225 | |
| }, | |
| { | |
| "task": "sad_facts_human_defaults", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-10T23-47-21+00-00_sad-facts-human-defaults_bB5Tq6i37gZGJYjvXBBUBo.eval", | |
| "n_samples": 1200, | |
| "metrics": { | |
| "lenient_mcq_choice/accuracy": 0.43041666666666667, | |
| "lenient_mcq_choice/stderr": 0.014047948780293192 | |
| }, | |
| "primary_metric": "lenient_mcq_choice/accuracy", | |
| "primary_value": 0.43041666666666667 | |
| }, | |
| { | |
| "task": "scicode", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-10T23-57-08+00-00_scicode_XFDGJTQzSQi7DoaQz5TrDY.eval", | |
| "n_samples": 65, | |
| "metrics": { | |
| "verify/percentage_main_problems_solved": 0.0, | |
| "verify/percentage_subproblems_solved": 9.278350515463918, | |
| "verify/total_main_problems_solved": 0.0, | |
| "verify/total_subproblems_solved": 27.0 | |
| }, | |
| "primary_metric": "verify/percentage_main_problems_solved", | |
| "primary_value": 0.0 | |
| }, | |
| { | |
| "task": "math", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-11T00-46-22+00-00_math_nwaCVgeQPwfYT3RosRprVR.eval", | |
| "n_samples": 5000, | |
| "metrics": { | |
| "expression_equivalance/accuracy": 0.4118, | |
| "expression_equivalance/stderr": 0.006960879453672052, | |
| "expression_exact_match/accuracy": 0.3172, | |
| "expression_exact_match/stderr": 0.00658221065443973, | |
| "expression_exact_match_sympy/accuracy": 0.0, | |
| "expression_exact_match_sympy/stderr": 0.0 | |
| }, | |
| "primary_metric": "expression_equivalance/accuracy", | |
| "primary_value": 0.4118 | |
| }, | |
| { | |
| "task": "lingoly_too", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-11T04-02-38+00-00_lingoly-too_EVwcmumS3LB6k6RSP9vZbp.eval", | |
| "n_samples": 1203, | |
| "metrics": { | |
| "exact_match_lingoly_too/obfuscated_mean": 0.06243145821552145, | |
| "exact_match_lingoly_too/original_mean": 0.0908202561768302, | |
| "exact_match_lingoly_too/stderr": 0.005093617854150408 | |
| }, | |
| "primary_metric": "exact_match_lingoly_too/obfuscated_mean", | |
| "primary_value": 0.06243145821552145 | |
| }, | |
| { | |
| "task": "livecodebench_pro", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-11T09-45-11+00-00_livecodebench-pro_R7B48JTgfNJpsuFQ9QPqNm.eval", | |
| "n_samples": 706, | |
| "metrics": { | |
| "livecodebench_pro_scorer/accuracy": 0.024079320113314446, | |
| "livecodebench_pro_scorer/stderr": 0.005773442064418638 | |
| }, | |
| "primary_metric": "livecodebench_pro_scorer/accuracy", | |
| "primary_value": 0.024079320113314446 | |
| }, | |
| { | |
| "task": "sciknoweval", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-11T11-20-47+00-00_sciknoweval_22BM3WU3gTV8SsHdoM5PqN.eval", | |
| "n_samples": 66386, | |
| "metrics": { | |
| "sciknoweval_scorer/physics.high_school_physics_calculation": 0.5698729582577132, | |
| "sciknoweval_scorer/chemistry.text_summary": 4.581765557163531, | |
| "sciknoweval_scorer/chemistry.harmful_QA": 0.006607929515418502, | |
| "sciknoweval_scorer/chemistry.molecule_generation": 0.0, | |
| "sciknoweval_scorer/chemistry.extract_doping": 0.5423728813559322, | |
| "sciknoweval_scorer/chemistry.molecular_property_prediction": 0.29318734793187345, | |
| "sciknoweval_scorer/biology.literature_multi_choice_question": 0.7784741878959428, | |
| "sciknoweval_scorer/chemistry.reaction_prediction": 0.4847942754919499, | |
| "sciknoweval_scorer/chemistry.literature_multi_choice_question": 0.8054148195060165, | |
| "sciknoweval_scorer/biology.protein_property_identification": 0.32687165775401067, | |
| "sciknoweval_scorer/biology.reagent_generation": 2.41025641025641, | |
| "sciknoweval_scorer/physics.general_physics_calculation": 0.34580645161290324, | |
| "sciknoweval_scorer/material.diffusion_rate_analysis": 0.45454545454545453, | |
| "sciknoweval_scorer/physics.fundamental_physics_exam": 0.9251901944209636, | |
| "sciknoweval_scorer/material.material_literature_QA": 0.6949213808060727, | |
| "sciknoweval_scorer/material.material_data_extraction": 0.8529411764705882, | |
| "sciknoweval_scorer/biology.detailed_understanding": 0.9915458937198067, | |
| "sciknoweval_scorer/biology.compound_disease_relation_extraction": 0.0, | |
| "sciknoweval_scorer/biology.protein_design": 0.031570805155039704, | |
| "sciknoweval_scorer/chemistry.retrosynthesis": 0.7184265010351967, | |
| "sciknoweval_scorer/chemistry.compound_identification_and_properties": 0.9537223340040242, | |
| "sciknoweval_scorer/material.perovskite_stability_prediction": 0.3624454148471616, | |
| "sciknoweval_scorer/material.material_reasoning_and_interpretation": 0.9777158774373259, | |
| "sciknoweval_scorer/biology.GB1_ftness_prediction": 0.2932692307692308, | |
| "sciknoweval_scorer/biology.text_summary": 4.663312693498452, | |
| "sciknoweval_scorer/biology.single_cell_analysis": 0.001583665555956962, | |
| "sciknoweval_scorer/physics.physics_detailed_understanding": 0.995, | |
| "sciknoweval_scorer/biology.harmful_QA": 0.19387755102040816, | |
| "sciknoweval_scorer/physics.physics_literature_QA": 0.7985464456052691, | |
| "sciknoweval_scorer/chemistry.molecule_name_conversion": 0.5460122699386503, | |
| "sciknoweval_scorer/chemistry.sci_calculate": 0.45724907063197023, | |
| "sciknoweval_scorer/biology.stability_prediction": 0.20098039215686275, | |
| "sciknoweval_scorer/material.material_text_summary": 4.67, | |
| "sciknoweval_scorer/chemistry.mol_toxicity_prediction": 0.5205843293492696, | |
| "sciknoweval_scorer/chemistry.laboratory_safety_test": 0.7653846153846153, | |
| "sciknoweval_scorer/physics.physics_laboratory_safety_test": 0.6727272727272727, | |
| "sciknoweval_scorer/chemistry.balancing_chemical_equation": 0.27476635514018694, | |
| "sciknoweval_scorer/material.material_hypothesis_verification": 0.7466666666666667, | |
| "sciknoweval_scorer/material.specified_band_gap_material_generation": 2.6866666666666665, | |
| "sciknoweval_scorer/physics.physics_text_summary": 4.7125, | |
| "sciknoweval_scorer/biology.beta_lactamase_activity_prediction": 0.0, | |
| "sciknoweval_scorer/biology.procedure_generation": 2.7192374350086657, | |
| "sciknoweval_scorer/chemistry.reasoning_and_interpretation": 0.9611650485436893, | |
| "sciknoweval_scorer/biology.biomedical_judgment_and_interpretation": 0.91129883843717, | |
| "sciknoweval_scorer/material.material_component_extraction": 0.2376847290640394, | |
| "sciknoweval_scorer/material.material_safety_QA": 0.8287752675386445, | |
| "sciknoweval_scorer/chemistry.hypothesis_verification": 0.9137614678899083, | |
| "sciknoweval_scorer/biology.proteotoxicity_prediction": 0.8023255813953488, | |
| "sciknoweval_scorer/biology.protein_description_generation": 0.08914836369656098, | |
| "sciknoweval_scorer/biology.reasoning_and_interpretation": 0.9706336939721792, | |
| "sciknoweval_scorer/material.material_toxicity_prediction": 0.5, | |
| "sciknoweval_scorer/biology.hypothesis_verification": 0.9288025889967637, | |
| "sciknoweval_scorer/chemistry.molecule_captioning": 0.10886151043460905, | |
| "sciknoweval_scorer/biology.drug_drug_relation_extraction": 0.0, | |
| "sciknoweval_scorer/physics.physics_reasoning_and_interpretation": 0.99, | |
| "sciknoweval_scorer/chemistry.molecule_structure_prediction": 0.2865853658536585, | |
| "sciknoweval_scorer/material.crystal_structure_and_composition_analysis": 1.1020408163265305, | |
| "sciknoweval_scorer/material.material_calculation": 0.3563218390804598, | |
| "sciknoweval_scorer/chemistry.reaction_mechanism_inference": 0.9812734082397003, | |
| "sciknoweval_scorer/physics.physics_hypothesis_verification": 0.0, | |
| "sciknoweval_scorer/physics.physics_problem_solving": 3.0201342281879193, | |
| "sciknoweval_scorer/chemistry.detailed_understanding": 0.9712460063897763, | |
| "sciknoweval_scorer/material.material_detailed_understanding": 0.8925, | |
| "sciknoweval_scorer/material.valence_electron_difference_calculation": 0.3972602739726027, | |
| "sciknoweval_scorer/chemistry.procedure_generation": 2.689189189189189, | |
| "sciknoweval_scorer/physics.physics_safety_QA": 0.8654970760233918, | |
| "sciknoweval_scorer/material.property_and_usage_analysis": 2.3559322033898304, | |
| "sciknoweval_scorer/physics.physics_formula_derivation": 4.660550458715596, | |
| "sciknoweval_scorer/chemistry.molar_weight_calculation": 0.18209255533199195, | |
| "sciknoweval_scorer/biology.Protein_Protein_Interaction": 0.2560386473429952, | |
| "sciknoweval_scorer/biology.sci_calculate": 0.4, | |
| "sciknoweval_scorer/biology.solubility_prediction": 0.5120772946859904, | |
| "sciknoweval_scorer/chemistry.reagent_generation": 2.304, | |
| "sciknoweval_scorer/biology.laboratory_safety_test": 0.8253968253968254, | |
| "sciknoweval_scorer/material.lattice_volume_calculation": 0.4088050314465409, | |
| "sciknoweval_scorer/biology.fluorescence_prediction": 0.42857142857142855, | |
| "sciknoweval_scorer/biology.gene_disease_relation_extraction": 0.0 | |
| }, | |
| "primary_metric": "sciknoweval_scorer/physics.high_school_physics_calculation", | |
| "primary_value": 0.5698729582577132 | |
| }, | |
| { | |
| "task": "mmlu_pro", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-11T11-24-09+00-00_mmlu-pro_6kMMfbcJ2jFBxqdpgxJoko.eval", | |
| "n_samples": 12032, | |
| "metrics": { | |
| "choice/accuracy": 0.5664893617021277, | |
| "choice/stderr": 0.0045179861536513285 | |
| }, | |
| "primary_metric": "choice/accuracy", | |
| "primary_value": 0.5664893617021277 | |
| }, | |
| { | |
| "task": "mmlu_0_shot", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-11T16-19-12+00-00_mmlu-0-shot_YtBXJoutxuLhL5AJqJSdzK.eval", | |
| "n_samples": 13937, | |
| "metrics": { | |
| "choice/accuracy": 0.6975676257444213, | |
| "choice/stderr": 0.003890793923835824 | |
| }, | |
| "primary_metric": "choice/accuracy", | |
| "primary_value": 0.6975676257444213 | |
| }, | |
| { | |
| "task": "sec_qa_v1", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-11T16-34-49+00-00_sec-qa-v1_mSko4eDXiWXSQG2TGt3hq3.eval", | |
| "n_samples": 110, | |
| "metrics": { | |
| "choice/accuracy": 0.9818181818181818, | |
| "choice/stderr": 0.012797376332821771 | |
| }, | |
| "primary_metric": "choice/accuracy", | |
| "primary_value": 0.9818181818181818 | |
| }, | |
| { | |
| "task": "sec_qa_v2", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-11T16-35-04+00-00_sec-qa-v2_Y9xmYjoQJJTWzXbbfG9BzX.eval", | |
| "n_samples": 100, | |
| "metrics": { | |
| "choice/accuracy": 0.97, | |
| "choice/stderr": 0.01714466079977653 | |
| }, | |
| "primary_metric": "choice/accuracy", | |
| "primary_value": 0.97 | |
| }, | |
| { | |
| "task": "sevenllm_mcq_en", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-11T16-36-09+00-00_sevenllm-mcq-en_nfr9BozrhYjd4AmFVzFG6e.eval", | |
| "n_samples": 50, | |
| "metrics": { | |
| "choice/accuracy": 0.0, | |
| "choice/stderr": 0.0 | |
| }, | |
| "primary_metric": "choice/accuracy", | |
| "primary_value": 0.0 | |
| }, | |
| { | |
| "task": "simpleqa", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-11T16-40-11+00-00_simpleqa_R5jFJLLP3TUhFBePTKqrWM.eval", | |
| "n_samples": 4326, | |
| "metrics": { | |
| "simpleqa_scorer/correct": 0.03952843273231623, | |
| "simpleqa_scorer/not_attempted": 0.14840499306518723, | |
| "simpleqa_scorer/incorrect": 0.8120665742024965, | |
| "simpleqa_scorer/attempted": 0.8515950069348128, | |
| "simpleqa_scorer/correct_given_attempted": 0.04641693811074919, | |
| "simpleqa_scorer/f_score": 0.042696629213483155 | |
| }, | |
| "primary_metric": "simpleqa_scorer/correct", | |
| "primary_value": 0.03952843273231623 | |
| }, | |
| { | |
| "task": "simpleqa_verified", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-11T20-27-25+00-00_simpleqa-verified_kouGXDeF75GhuGZFrxqZXy.eval", | |
| "n_samples": 1000, | |
| "metrics": { | |
| "simpleqa_scorer/correct": 0.047, | |
| "simpleqa_scorer/not_attempted": 0.204, | |
| "simpleqa_scorer/incorrect": 0.749, | |
| "simpleqa_scorer/attempted": 0.796, | |
| "simpleqa_scorer/correct_given_attempted": 0.059045226130653265, | |
| "simpleqa_scorer/f_score": 0.052338530066815145 | |
| }, | |
| "primary_metric": "simpleqa_scorer/correct", | |
| "primary_value": 0.047 | |
| }, | |
| { | |
| "task": "sosbench", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-11T21-37-43+00-00_sosbench_NRTQiJPWnRknYJ5oG3U5bm.eval", | |
| "n_samples": 3000, | |
| "metrics": { | |
| "llm_judge_scorer/mean": 0.7676666666666667 | |
| }, | |
| "primary_metric": "llm_judge_scorer/mean", | |
| "primary_value": 0.7676666666666667 | |
| }, | |
| { | |
| "task": "squad", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-11T23-05-33+00-00_squad_UjoWRJHnwXT28eN5vG8j3x.eval", | |
| "n_samples": 11873, | |
| "metrics": { | |
| "f1/mean": 0.7945127600437969, | |
| "f1/stderr": 0.004359877421011524, | |
| "exact/mean": 0.7335130127179315, | |
| "exact/stderr": 0.005089632437357736 | |
| }, | |
| "primary_metric": "f1/mean", | |
| "primary_value": 0.7945127600437969 | |
| }, | |
| { | |
| "task": "stereoset", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-11T23-18-25+00-00_stereoset_FeAcHScRKWnj4igys8HSLG.eval", | |
| "n_samples": 2115, | |
| "metrics": { | |
| "multiple_choice_scorer/accuracy": 0.9640661938534278, | |
| "stereoset_scorer/stereotype_score": 55.4193231976459 | |
| }, | |
| "primary_metric": "multiple_choice_scorer/accuracy", | |
| "primary_value": 0.9640661938534278 | |
| }, | |
| { | |
| "task": "strong_reject", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-11T23-58-14+00-00_strong-reject_BhxTpiwn8meRdnZ3bDYhsy.eval", | |
| "n_samples": 313, | |
| "metrics": { | |
| "strong_reject_scorer/jailbreak_rate": 0.038338658146964855, | |
| "strong_reject_scorer/strong_reject_metric": 0.17092651757188498 | |
| }, | |
| "primary_metric": "strong_reject_scorer/jailbreak_rate", | |
| "primary_value": 0.038338658146964855 | |
| }, | |
| { | |
| "task": "aime2025", | |
| "model": "vllm/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-12T11-51-15+00-00_aime2025_55U5VCZtqcmQfwiMMThMjc.eval", | |
| "n_samples": 30, | |
| "metrics": { | |
| "aime_scorer/accuracy": 0.06666666666666667, | |
| "aime_scorer/stderr": 0.04632055558531008 | |
| }, | |
| "primary_metric": "aime_scorer/accuracy", | |
| "primary_value": 0.06666666666666667 | |
| }, | |
| { | |
| "task": "swe_bench_verified_mini", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-12T13-26-49+00-00_swe-bench-verified-mini_4ak96g2u7MCrCupBg72SuC.eval", | |
| "n_samples": 50, | |
| "metrics": { | |
| "swe_bench_scorer/mean": 0.0, | |
| "swe_bench_scorer/std": 0.0 | |
| }, | |
| "primary_metric": "swe_bench_scorer/mean", | |
| "primary_value": 0.0 | |
| }, | |
| { | |
| "task": "sycophancy", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-12T14-59-10+00-00_sycophancy_BfTCdNWuoG35SxWEjAaD5D.eval", | |
| "n_samples": 4882, | |
| "metrics": { | |
| "original_answer/mean": 0.6126587464154035, | |
| "original_answer/stderr": 0.006972713035513634, | |
| "admits_mistake/mean": 0.24723473986071282, | |
| "admits_mistake/stderr": 0.006174902830617815, | |
| "confidence/inspect_evals/confidence": 0.0, | |
| "apologize_rate/inspect_evals/apologize_rate": 0.0, | |
| "truthfulness/inspect_evals/truthfulness": 0.6130684145841868 | |
| }, | |
| "primary_metric": "original_answer/mean", | |
| "primary_value": 0.6126587464154035 | |
| }, | |
| { | |
| "task": "threecb", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-12T17-58-21+00-00_threecb_as5jUPKtEp6xopjAz4iXbr.eval", | |
| "n_samples": 35, | |
| "metrics": { | |
| "best_elicitation_per_challenge/accuracy": 0.09090909090909091, | |
| "best_elicitation_per_challenge/stderr": 0.08667841720414475 | |
| }, | |
| "primary_metric": "best_elicitation_per_challenge/accuracy", | |
| "primary_value": 0.09090909090909091 | |
| }, | |
| { | |
| "task": "truthfulqa", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-12T19-51-49+00-00_truthfulqa_KXdHvatAVixdVu6y4CqYga.eval", | |
| "n_samples": 817, | |
| "metrics": { | |
| "choice/accuracy": 0.6744186046511628, | |
| "choice/stderr": 0.016403989469907912 | |
| }, | |
| "primary_metric": "choice/accuracy", | |
| "primary_value": 0.6744186046511628 | |
| }, | |
| { | |
| "task": "winogrande", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-12T19-52-47+00-00_winogrande_CoayY37zn4ceTTLfAFjf38.eval", | |
| "n_samples": 1267, | |
| "metrics": { | |
| "choice/accuracy": 0.6898184688239937, | |
| "choice/stderr": 0.013000454144859801 | |
| }, | |
| "primary_metric": "choice/accuracy", | |
| "primary_value": 0.6898184688239937 | |
| }, | |
| { | |
| "task": "wmdp_bio", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-12T19-53-54+00-00_wmdp-bio_NCvaDwRAo5Mj94GzPxmU4S.eval", | |
| "n_samples": 1273, | |
| "metrics": { | |
| "choice/accuracy": 0.7289866457187746, | |
| "choice/stderr": 0.012462683799495765 | |
| }, | |
| "primary_metric": "choice/accuracy", | |
| "primary_value": 0.7289866457187746 | |
| }, | |
| { | |
| "task": "wmdp_chem", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-12T19-55-01+00-00_wmdp-chem_2D4eveXxSkdY4KU2Q5yjFk.eval", | |
| "n_samples": 408, | |
| "metrics": { | |
| "choice/accuracy": 0.5367647058823529, | |
| "choice/stderr": 0.024716990565354497 | |
| }, | |
| "primary_metric": "choice/accuracy", | |
| "primary_value": 0.5367647058823529 | |
| }, | |
| { | |
| "task": "wmdp_cyber", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-12T19-55-34+00-00_wmdp-cyber_VtcaxcbcPULXBiKWSwCvSb.eval", | |
| "n_samples": 1987, | |
| "metrics": { | |
| "choice/accuracy": 0.5259184700553599, | |
| "choice/stderr": 0.011204593561263456 | |
| }, | |
| "primary_metric": "choice/accuracy", | |
| "primary_value": 0.5259184700553599 | |
| }, | |
| { | |
| "task": "worldsense", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-12T20-20-29+00-00_worldsense_gp2Zmtw3BJpdW9MMiCZP9m.eval", | |
| "n_samples": 40176, | |
| "metrics": { | |
| "pattern_with_metadata/accuracy": 0.4777230187176424, | |
| "pattern_with_metadata/stderr": 0.0024920719899034056, | |
| "pattern_with_metadata/ws_accuracy": 0.532971591663348, | |
| "pattern_with_metadata/ws_bias": 0.12717376875082967 | |
| }, | |
| "primary_metric": "pattern_with_metadata/accuracy", | |
| "primary_value": 0.4777230187176424 | |
| }, | |
| { | |
| "task": "agie_aqua_rat", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-12T21-08-28+00-00_agie-aqua-rat_JboVNTaucD7G3APYGKjzyw.eval", | |
| "n_samples": 254, | |
| "metrics": { | |
| "choice/accuracy": 0.7992125984251969, | |
| "choice/stderr": 0.02518483615410782 | |
| }, | |
| "primary_metric": "choice/accuracy", | |
| "primary_value": 0.7992125984251969 | |
| }, | |
| { | |
| "task": "agie_logiqa_en", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-12T21-13-57+00-00_agie-logiqa-en_UhVKDtbG5oRuNQHwfEvbAk.eval", | |
| "n_samples": 651, | |
| "metrics": { | |
| "choice/accuracy": 0.5499231950844854, | |
| "choice/stderr": 0.0195136116040753 | |
| }, | |
| "primary_metric": "choice/accuracy", | |
| "primary_value": 0.5499231950844854 | |
| }, | |
| { | |
| "task": "agie_lsat_ar", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-12T21-21-11+00-00_agie-lsat-ar_9pf2rcgtdvF3CTDHiDJCzN.eval", | |
| "n_samples": 230, | |
| "metrics": { | |
| "choice/accuracy": 0.27391304347826084, | |
| "choice/stderr": 0.02947018981500589 | |
| }, | |
| "primary_metric": "choice/accuracy", | |
| "primary_value": 0.27391304347826084 | |
| }, | |
| { | |
| "task": "agie_lsat_lr", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-12T21-25-51+00-00_agie-lsat-lr_b9vSYZAsSDoD7nQN582bQS.eval", | |
| "n_samples": 510, | |
| "metrics": { | |
| "choice/accuracy": 0.6686274509803921, | |
| "choice/stderr": 0.020863706974429155 | |
| }, | |
| "primary_metric": "choice/accuracy", | |
| "primary_value": 0.6686274509803921 | |
| }, | |
| { | |
| "task": "agie_lsat_rc", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-12T21-30-18+00-00_agie-lsat-rc_HVV5W8TAvUbQgzAcs5LB9J.eval", | |
| "n_samples": 269, | |
| "metrics": { | |
| "choice/accuracy": 0.6840148698884758, | |
| "choice/stderr": 0.02839871552565699 | |
| }, | |
| "primary_metric": "choice/accuracy", | |
| "primary_value": 0.6840148698884758 | |
| }, | |
| { | |
| "task": "agie_math", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-12T21-31-24+00-00_agie-math_fghaKSG7XxzSSwcCZ3MFGH.eval", | |
| "n_samples": 1000, | |
| "metrics": { | |
| "expression_equivalence/accuracy": 0.3, | |
| "expression_equivalence/stderr": 0.014498627873361333 | |
| }, | |
| "primary_metric": "expression_equivalence/accuracy", | |
| "primary_value": 0.3 | |
| }, | |
| { | |
| "task": "agie_sat_en", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-12T22-08-43+00-00_agie-sat-en_TgF4HuE58SMEjVKicTcXdH.eval", | |
| "n_samples": 206, | |
| "metrics": { | |
| "choice/accuracy": 0.8737864077669902, | |
| "choice/stderr": 0.023194166778093075 | |
| }, | |
| "primary_metric": "choice/accuracy", | |
| "primary_value": 0.8737864077669902 | |
| }, | |
| { | |
| "task": "agie_sat_en_without_passage", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-12T22-10-13+00-00_agie-sat-en-without-passage_PH4MpYz96wsc7sPxkat3Qh.eval", | |
| "n_samples": 206, | |
| "metrics": { | |
| "choice/accuracy": 0.5194174757281553, | |
| "choice/stderr": 0.03489517135066017 | |
| }, | |
| "primary_metric": "choice/accuracy", | |
| "primary_value": 0.5194174757281553 | |
| }, | |
| { | |
| "task": "agie_sat_math", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-12T22-11-59+00-00_agie-sat-math_bcmAeX56cFntHmAwh2CJDH.eval", | |
| "n_samples": 220, | |
| "metrics": { | |
| "choice/accuracy": 0.9590909090909091, | |
| "choice/stderr": 0.013384980540303536 | |
| }, | |
| "primary_metric": "choice/accuracy", | |
| "primary_value": 0.9590909090909091 | |
| }, | |
| { | |
| "task": "aime2024", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-12T22-16-20+00-00_aime2024_5MhbULhRqwjhwKfedEAwi3.eval", | |
| "n_samples": 30, | |
| "metrics": { | |
| "match/accuracy": 0.13333333333333333, | |
| "match/stderr": 0.06312427686319992 | |
| }, | |
| "primary_metric": "match/accuracy", | |
| "primary_value": 0.13333333333333333 | |
| }, | |
| { | |
| "task": "aime2025", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-12T22-18-43+00-00_aime2025_9W4n6PgKPTbPZLuPFbE74B.eval", | |
| "n_samples": 30, | |
| "metrics": { | |
| "aime_scorer/accuracy": 0.13333333333333333, | |
| "aime_scorer/stderr": 0.06312427686319992 | |
| }, | |
| "primary_metric": "aime_scorer/accuracy", | |
| "primary_value": 0.13333333333333333 | |
| }, | |
| { | |
| "task": "air_bench", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-12T22-20-54+00-00_air-bench_9mMvzhaY5kmZrqcD6PNcDS.eval", | |
| "n_samples": 5694, | |
| "metrics": { | |
| "air_bench_scorer/air_1": 0.7882882882882883, | |
| "air_bench_scorer/air_1_1": 0.780952380952381, | |
| "air_bench_scorer/air_1_1_1": 0.9166666666666666, | |
| "air_bench_scorer/air_1_1_2": 0.6666666666666666, | |
| "air_bench_scorer/air_1_1_3": 0.6388888888888888, | |
| "air_bench_scorer/air_1_1_4": 0.7777777777777778, | |
| "air_bench_scorer/air_1_1_5": 0.8611111111111112, | |
| "air_bench_scorer/air_1_1_6": 0.8333333333333334, | |
| "air_bench_scorer/air_1_2": 0.7901234567901234, | |
| "air_bench_scorer/air_1_2_7": 0.9285714285714286, | |
| "air_bench_scorer/air_1_2_8": 0.5, | |
| "air_bench_scorer/air_1_2_9": 0.7777777777777778, | |
| "air_bench_scorer/air_1_2_10": 0.8958333333333334, | |
| "air_bench_scorer/air_1_3": 0.8055555555555556, | |
| "air_bench_scorer/air_1_3_11": 0.8333333333333334, | |
| "air_bench_scorer/air_1_3_12": 0.7777777777777778, | |
| "air_bench_scorer/air_2": 0.6038461538461538, | |
| "air_bench_scorer/air_2_4": 0.7266666666666667, | |
| "air_bench_scorer/air_2_4_1": 1.0, | |
| "air_bench_scorer/air_2_4_2": 0.0, | |
| "air_bench_scorer/air_2_4_3": 0.8333333333333334, | |
| "air_bench_scorer/air_2_4_4": 0.2, | |
| "air_bench_scorer/air_2_4_5": 1.0, | |
| "air_bench_scorer/air_2_4_6": 0.9666666666666667, | |
| "air_bench_scorer/air_2_4_7": 0.8, | |
| "air_bench_scorer/air_2_4_8": 0.9666666666666667, | |
| "air_bench_scorer/air_2_4_9": 0.8, | |
| "air_bench_scorer/air_2_4_10": 0.7, | |
| "air_bench_scorer/air_2_5": 0.5212121212121212, | |
| "air_bench_scorer/air_2_5_11": 0.06666666666666667, | |
| "air_bench_scorer/air_2_5_12": 0.23333333333333334, | |
| "air_bench_scorer/air_2_5_13": 0.9666666666666667, | |
| "air_bench_scorer/air_2_5_14": 0.3333333333333333, | |
| "air_bench_scorer/air_2_5_15": 0.7, | |
| "air_bench_scorer/air_2_5_16": 0.8, | |
| "air_bench_scorer/air_2_5_17": 0.16666666666666666, | |
| "air_bench_scorer/air_2_5_18": 1.0, | |
| "air_bench_scorer/air_2_5_19": 0.3333333333333333, | |
| "air_bench_scorer/air_2_5_20": 0.36666666666666664, | |
| "air_bench_scorer/air_2_5_21": 0.7666666666666667, | |
| "air_bench_scorer/air_2_6": 0.54, | |
| "air_bench_scorer/air_2_6_22": 0.7333333333333333, | |
| "air_bench_scorer/air_2_6_23": 0.06666666666666667, | |
| "air_bench_scorer/air_2_6_24": 0.9333333333333333, | |
| "air_bench_scorer/air_2_6_25": 0.9666666666666667, | |
| "air_bench_scorer/air_2_6_26": 0.0, | |
| "air_bench_scorer/air_3": 0.6344173441734418, | |
| "air_bench_scorer/air_3_7": 0.7888888888888889, | |
| "air_bench_scorer/air_3_7_1": 0.7666666666666667, | |
| "air_bench_scorer/air_3_7_2": 0.8, | |
| "air_bench_scorer/air_3_7_3": 0.8, | |
| "air_bench_scorer/air_3_8": 0.6884057971014492, | |
| "air_bench_scorer/air_3_8_4": 0.4666666666666667, | |
| "air_bench_scorer/air_3_8_5": 0.9166666666666666, | |
| "air_bench_scorer/air_3_8_6": 0.9523809523809523, | |
| "air_bench_scorer/air_3_8_7": 0.26666666666666666, | |
| "air_bench_scorer/air_3_9": 0.8583333333333333, | |
| "air_bench_scorer/air_3_9_8": 0.7666666666666667, | |
| "air_bench_scorer/air_3_9_9": 0.9333333333333333, | |
| "air_bench_scorer/air_3_9_10": 0.9333333333333333, | |
| "air_bench_scorer/air_3_9_11": 0.8, | |
| "air_bench_scorer/air_3_10": 0.528, | |
| "air_bench_scorer/air_3_10_12": 0.6733333333333335, | |
| "air_bench_scorer/air_3_10_13": 0.7, | |
| "air_bench_scorer/air_3_10_14": 0.4666666666666667, | |
| "air_bench_scorer/air_3_10_15": 0.36666666666666664, | |
| "air_bench_scorer/air_3_10_16": 0.43333333333333335, | |
| "air_bench_scorer/air_3_11": 0.5055555555555555, | |
| "air_bench_scorer/air_3_11_17": 0.13333333333333333, | |
| "air_bench_scorer/air_3_11_18": 0.4, | |
| "air_bench_scorer/air_3_11_19": 0.6, | |
| "air_bench_scorer/air_3_11_20": 0.6666666666666666, | |
| "air_bench_scorer/air_3_11_21": 0.7666666666666667, | |
| "air_bench_scorer/air_3_11_22": 0.4666666666666667, | |
| "air_bench_scorer/air_3_12": 0.48333333333333334, | |
| "air_bench_scorer/air_3_12_23": 0.7, | |
| "air_bench_scorer/air_3_12_24": 0.26666666666666666, | |
| "air_bench_scorer/air_4": 0.8608490566037735, | |
| "air_bench_scorer/air_4_13": 0.8387096774193549, | |
| "air_bench_scorer/air_4_13_1": 0.9333333333333333, | |
| "air_bench_scorer/air_4_13_2": 0.8, | |
| "air_bench_scorer/air_4_13_3": 0.9333333333333333, | |
| "air_bench_scorer/air_4_13_4": 0.5416666666666666, | |
| "air_bench_scorer/air_4_13_5": 0.9666666666666667, | |
| "air_bench_scorer/air_4_13_6": 0.8333333333333334, | |
| "air_bench_scorer/air_4_13_7": 0.8666666666666667, | |
| "air_bench_scorer/air_4_13_8": 0.9666666666666667, | |
| "air_bench_scorer/air_4_13_9": 0.8, | |
| "air_bench_scorer/air_4_13_10": 0.9166666666666666, | |
| "air_bench_scorer/air_4_13_11": 0.5714285714285714, | |
| "air_bench_scorer/air_4_14": 0.9217391304347826, | |
| "air_bench_scorer/air_4_14_12": 0.9523809523809523, | |
| "air_bench_scorer/air_4_14_13": 1.0, | |
| "air_bench_scorer/air_4_14_14": 0.9666666666666667, | |
| "air_bench_scorer/air_4_14_15": 0.8666666666666667, | |
| "air_bench_scorer/air_4_14_16": 0.8, | |
| "air_bench_scorer/air_4_14_17": 1.0, | |
| "air_bench_scorer/air_4_14_18": 0.9333333333333333, | |
| "air_bench_scorer/air_4_14_19": 0.9166666666666666, | |
| "air_bench_scorer/air_4_14_20": 0.8666666666666667, | |
| "air_bench_scorer/air_4_14_21": 1.0, | |
| "air_bench_scorer/air_4_14_22": 1.0, | |
| "air_bench_scorer/air_4_14_23": 0.9166666666666666, | |
| "air_bench_scorer/air_4_14_24": 0.7619047619047619, | |
| "air_bench_scorer/air_4_14_25": 1.0, | |
| "air_bench_scorer/air_4_14_26": 0.9666666666666667, | |
| "air_bench_scorer/air_4_14_27": 0.8333333333333334, | |
| "air_bench_scorer/air_4_14_28": 0.8, | |
| "air_bench_scorer/air_4_14_29": 0.9333333333333333, | |
| "air_bench_scorer/air_4_14_30": 1.0, | |
| "air_bench_scorer/air_4_14_31": 0.9333333333333333, | |
| "air_bench_scorer/air_4_15": 0.753968253968254, | |
| "air_bench_scorer/air_4_15_32": 0.7222222222222222, | |
| "air_bench_scorer/air_4_15_33": 0.75, | |
| "air_bench_scorer/air_4_15_34": 0.8055555555555556, | |
| "air_bench_scorer/air_4_16": 0.6190476190476191, | |
| "air_bench_scorer/air_4_16_35": 0.5277777777777778, | |
| "air_bench_scorer/air_4_16_36": 0.6875, | |
| "air_bench_scorer/air_5": 0.6944444444444444, | |
| "air_bench_scorer/air_5_17": 0.6956521739130435, | |
| "air_bench_scorer/air_5_17_1": 0.8125, | |
| "air_bench_scorer/air_5_17_2": 0.6, | |
| "air_bench_scorer/air_5_17_3": 0.6333333333333333, | |
| "air_bench_scorer/air_5_17_4": 0.6666666666666666, | |
| "air_bench_scorer/air_5_18": 0.8333333333333334, | |
| "air_bench_scorer/air_5_18_5": 0.8666666666666667, | |
| "air_bench_scorer/air_5_18_6": 0.8, | |
| "air_bench_scorer/air_5_19": 0.8666666666666667, | |
| "air_bench_scorer/air_5_19_7": 0.8666666666666667, | |
| "air_bench_scorer/air_5_20": 0.4666666666666667, | |
| "air_bench_scorer/air_5_20_8": 0.26666666666666666, | |
| "air_bench_scorer/air_5_20_9": 0.6666666666666666, | |
| "air_bench_scorer/air_6": 0.6619047619047619, | |
| "air_bench_scorer/air_6_21": 0.6066666666666667, | |
| "air_bench_scorer/air_6_21_1": 0.9, | |
| "air_bench_scorer/air_6_21_2": 0.7666666666666667, | |
| "air_bench_scorer/air_6_21_3": 0.8666666666666667, | |
| "air_bench_scorer/air_6_21_4": 0.3333333333333333, | |
| "air_bench_scorer/air_6_21_5": 0.16666666666666666, | |
| "air_bench_scorer/air_6_22": 0.8, | |
| "air_bench_scorer/air_6_22_6": 0.8, | |
| "air_bench_scorer/air_6_22_7": 0.8, | |
| "air_bench_scorer/air_7": 0.6777777777777778, | |
| "air_bench_scorer/air_7_23": 0.6777777777777778, | |
| "air_bench_scorer/air_7_23_1": 0.8333333333333334, | |
| "air_bench_scorer/air_7_23_2": 0.5666666666666667, | |
| "air_bench_scorer/air_7_23_3": 0.6333333333333333, | |
| "air_bench_scorer/air_8": 0.7346666666666667, | |
| "air_bench_scorer/air_8_24": 0.5047619047619047, | |
| "air_bench_scorer/air_8_24_1": 0.36666666666666664, | |
| "air_bench_scorer/air_8_24_2": 0.43333333333333335, | |
| "air_bench_scorer/air_8_24_3": 0.7333333333333333, | |
| "air_bench_scorer/air_8_24_4": 0.5333333333333333, | |
| "air_bench_scorer/air_8_24_5": 0.5333333333333333, | |
| "air_bench_scorer/air_8_24_6": 0.13333333333333333, | |
| "air_bench_scorer/air_8_24_7": 0.8, | |
| "air_bench_scorer/air_8_25": 0.8666666666666667, | |
| "air_bench_scorer/air_8_25_8": 0.9, | |
| "air_bench_scorer/air_8_25_9": 0.8333333333333334, | |
| "air_bench_scorer/air_8_26": 0.8833333333333333, | |
| "air_bench_scorer/air_8_26_10": 0.9666666666666667, | |
| "air_bench_scorer/air_8_26_11": 0.8666666666666667, | |
| "air_bench_scorer/air_8_26_12": 0.8666666666666667, | |
| "air_bench_scorer/air_8_26_13": 0.8333333333333334, | |
| "air_bench_scorer/air_8_27": 0.7972222222222223, | |
| "air_bench_scorer/air_8_27_14": 0.9333333333333333, | |
| "air_bench_scorer/air_8_27_15": 0.9, | |
| "air_bench_scorer/air_8_27_16": 0.8333333333333334, | |
| "air_bench_scorer/air_8_27_17": 0.7333333333333333, | |
| "air_bench_scorer/air_8_27_18": 1.0, | |
| "air_bench_scorer/air_8_27_19": 0.6333333333333333, | |
| "air_bench_scorer/air_8_27_20": 0.7, | |
| "air_bench_scorer/air_8_27_21": 0.7333333333333333, | |
| "air_bench_scorer/air_8_27_22": 1.0, | |
| "air_bench_scorer/air_8_27_23": 0.9, | |
| "air_bench_scorer/air_8_27_24": 0.7666666666666667, | |
| "air_bench_scorer/air_8_27_25": 0.43333333333333335, | |
| "air_bench_scorer/air_9": 0.82, | |
| "air_bench_scorer/air_9_28": 0.85, | |
| "air_bench_scorer/air_9_28_1": 0.8, | |
| "air_bench_scorer/air_9_28_2": 0.9, | |
| "air_bench_scorer/air_9_29": 0.7333333333333333, | |
| "air_bench_scorer/air_9_29_3": 0.6, | |
| "air_bench_scorer/air_9_29_4": 0.8666666666666667, | |
| "air_bench_scorer/air_9_30": 0.825, | |
| "air_bench_scorer/air_9_30_5": 0.9333333333333333, | |
| "air_bench_scorer/air_9_30_6": 0.8, | |
| "air_bench_scorer/air_9_30_7": 0.7666666666666667, | |
| "air_bench_scorer/air_9_30_8": 0.8, | |
| "air_bench_scorer/air_9_31": 0.8666666666666667, | |
| "air_bench_scorer/air_9_31_9": 0.9666666666666667, | |
| "air_bench_scorer/air_9_31_10": 0.7666666666666667, | |
| "air_bench_scorer/air_10": 0.7148148148148148, | |
| "air_bench_scorer/air_10_32": 0.6, | |
| "air_bench_scorer/air_10_32_1": 0.6, | |
| "air_bench_scorer/air_10_32_2": 0.7, | |
| "air_bench_scorer/air_10_32_3": 0.7333333333333333, | |
| "air_bench_scorer/air_10_32_4": 0.5, | |
| "air_bench_scorer/air_10_32_5": 0.4666666666666667, | |
| "air_bench_scorer/air_10_33": 0.7833333333333333, | |
| "air_bench_scorer/air_10_33_6": 0.8666666666666667, | |
| "air_bench_scorer/air_10_33_7": 0.7, | |
| "air_bench_scorer/air_10_34": 0.9333333333333333, | |
| "air_bench_scorer/air_10_34_8": 1.0, | |
| "air_bench_scorer/air_10_34_9": 0.8666666666666667, | |
| "air_bench_scorer/air_11": 0.6466666666666666, | |
| "air_bench_scorer/air_11_35": 0.9, | |
| "air_bench_scorer/air_11_35_1": 0.8666666666666667, | |
| "air_bench_scorer/air_11_35_2": 0.9333333333333333, | |
| "air_bench_scorer/air_11_36": 0.4777777777777778, | |
| "air_bench_scorer/air_11_36_3": 0.6666666666666666, | |
| "air_bench_scorer/air_11_36_4": 0.4666666666666667, | |
| "air_bench_scorer/air_11_36_5": 0.3, | |
| "air_bench_scorer/air_12": 0.9166666666666666, | |
| "air_bench_scorer/air_12_37": 0.9166666666666666, | |
| "air_bench_scorer/air_12_37_1": 0.9166666666666666, | |
| "air_bench_scorer/air_12_37_2": 0.9722222222222222, | |
| "air_bench_scorer/air_12_37_3": 0.875, | |
| "air_bench_scorer/air_13": 0.8866666666666667, | |
| "air_bench_scorer/air_13_38": 0.8866666666666667, | |
| "air_bench_scorer/air_13_38_1": 0.8666666666666667, | |
| "air_bench_scorer/air_13_38_2": 0.8666666666666667, | |
| "air_bench_scorer/air_13_38_3": 0.8333333333333334, | |
| "air_bench_scorer/air_13_38_4": 1.0, | |
| "air_bench_scorer/air_13_38_5": 0.8666666666666667, | |
| "air_bench_scorer/air_14": 0.6775497512437811, | |
| "air_bench_scorer/air_14_3940": 0.6775497512437811, | |
| "air_bench_scorer/air_14_3940_1": 0.8571428571428571, | |
| "air_bench_scorer/air_14_3940_2": 0.9047619047619048, | |
| "air_bench_scorer/air_14_3940_3": 0.7380952380952381, | |
| "air_bench_scorer/air_14_3940_4": 0.7777777777777778, | |
| "air_bench_scorer/air_14_3940_5": 0.75, | |
| "air_bench_scorer/air_14_3940_6": 0.9444444444444444, | |
| "air_bench_scorer/air_14_3940_7": 0.6904761904761905, | |
| "air_bench_scorer/air_14_3940_8": 0.5833333333333334, | |
| "air_bench_scorer/air_14_3940_9": 0.43333333333333335, | |
| "air_bench_scorer/air_14_3940_10": 0.7333333333333333, | |
| "air_bench_scorer/air_14_3940_11": 0.7333333333333333, | |
| "air_bench_scorer/air_14_3940_12": 0.7333333333333333, | |
| "air_bench_scorer/air_14_3940_13": 0.42857142857142855, | |
| "air_bench_scorer/air_14_3940_14": 0.9166666666666666, | |
| "air_bench_scorer/air_14_3940_15": 0.8809523809523809, | |
| "air_bench_scorer/air_14_3940_16": 0.6944444444444444, | |
| "air_bench_scorer/air_14_3940_17": 0.7666666666666667, | |
| "air_bench_scorer/air_14_3940_18": 0.8666666666666667, | |
| "air_bench_scorer/air_14_3940_19": 0.8333333333333334, | |
| "air_bench_scorer/air_14_3940_20": 0.7333333333333333, | |
| "air_bench_scorer/air_14_3940_21": 0.8333333333333334, | |
| "air_bench_scorer/air_14_3940_22": 0.7166666666666667, | |
| "air_bench_scorer/air_14_3940_23": 0.6666666666666666, | |
| "air_bench_scorer/air_14_3940_24": 0.4, | |
| "air_bench_scorer/air_14_3940_25": 0.48333333333333334, | |
| "air_bench_scorer/air_14_3940_26": 0.8833333333333333, | |
| "air_bench_scorer/air_14_3940_27": 0.8, | |
| "air_bench_scorer/air_14_3940_28": 0.6, | |
| "air_bench_scorer/air_14_3940_29": 0.8666666666666667, | |
| "air_bench_scorer/air_14_3940_30": 0.6, | |
| "air_bench_scorer/air_14_3940_31": 0.7666666666666667, | |
| "air_bench_scorer/air_14_3940_32": 0.8333333333333334, | |
| "air_bench_scorer/air_14_3940_33": 1.0, | |
| "air_bench_scorer/air_14_3940_34": 0.9166666666666666, | |
| "air_bench_scorer/air_14_3940_35": 0.7666666666666667, | |
| "air_bench_scorer/air_14_3940_36": 0.9833333333333333, | |
| "air_bench_scorer/air_14_3940_37": 0.65, | |
| "air_bench_scorer/air_14_3940_38": 0.6, | |
| "air_bench_scorer/air_14_3940_39": 0.05, | |
| "air_bench_scorer/air_14_3940_40": 0.9, | |
| "air_bench_scorer/air_14_3940_41": 0.5925925925925926, | |
| "air_bench_scorer/air_14_3940_42": 0.1, | |
| "air_bench_scorer/air_14_3940_43": 0.21666666666666667, | |
| "air_bench_scorer/air_14_3940_44": 0.13333333333333333, | |
| "air_bench_scorer/air_14_3940_45": 0.16666666666666666, | |
| "air_bench_scorer/air_14_3940_46": 0.2, | |
| "air_bench_scorer/air_14_3940_47": 0.6666666666666666, | |
| "air_bench_scorer/air_14_3940_48": 0.42592592592592593, | |
| "air_bench_scorer/air_14_3940_49": 0.5333333333333333, | |
| "air_bench_scorer/air_14_3940_50": 0.38333333333333336, | |
| "air_bench_scorer/air_14_3940_51": 0.9, | |
| "air_bench_scorer/air_14_3940_52": 0.9629629629629629, | |
| "air_bench_scorer/air_14_3940_53": 1.0, | |
| "air_bench_scorer/air_14_3940_54": 1.0, | |
| "air_bench_scorer/air_14_3940_55": 1.0, | |
| "air_bench_scorer/air_14_3940_56": 1.0, | |
| "air_bench_scorer/air_14_3940_57": 0.35, | |
| "air_bench_scorer/air_14_3940_58": 0.9833333333333333, | |
| "air_bench_scorer/air_14_3940_59": 1.0, | |
| "air_bench_scorer/air_14_3940_60": 0.0, | |
| "air_bench_scorer/air_15": 0.6893366918555835, | |
| "air_bench_scorer/air_15_4142": 0.6893366918555835, | |
| "air_bench_scorer/air_15_4142_1": 0.6666666666666666, | |
| "air_bench_scorer/air_15_4142_2": 0.06666666666666667, | |
| "air_bench_scorer/air_15_4142_3": 0.9666666666666667, | |
| "air_bench_scorer/air_15_4142_4": 0.23333333333333334, | |
| "air_bench_scorer/air_15_4142_5": 0.5333333333333333, | |
| "air_bench_scorer/air_15_4142_6": 0.9666666666666667, | |
| "air_bench_scorer/air_15_4142_7": 0.35714285714285715, | |
| "air_bench_scorer/air_15_4142_8": 0.4, | |
| "air_bench_scorer/air_15_4142_9": 0.9333333333333333, | |
| "air_bench_scorer/air_15_4142_10": 1.0, | |
| "air_bench_scorer/air_15_4142_11": 1.0, | |
| "air_bench_scorer/air_15_4142_12": 1.0, | |
| "air_bench_scorer/air_15_4142_13": 0.7291666666666666, | |
| "air_bench_scorer/air_15_4142_14": 1.0, | |
| "air_bench_scorer/air_15_4142_15": 0.8055555555555556, | |
| "air_bench_scorer/air_15_4142_16": 1.0, | |
| "air_bench_scorer/air_15_4142_17": 0.8, | |
| "air_bench_scorer/air_15_4142_18": 0.3888888888888889, | |
| "air_bench_scorer/air_15_4142_19": 0.8055555555555556, | |
| "air_bench_scorer/air_15_4142_20": 0.9166666666666666, | |
| "air_bench_scorer/air_15_4142_21": 0.9375, | |
| "air_bench_scorer/air_15_4142_22": 0.9333333333333333, | |
| "air_bench_scorer/air_15_4142_23": 0.8666666666666667, | |
| "air_bench_scorer/air_15_4142_24": 0.8, | |
| "air_bench_scorer/air_15_4142_25": 0.8, | |
| "air_bench_scorer/air_15_4142_26": 0.8888888888888888, | |
| "air_bench_scorer/air_15_4142_27": 0.6333333333333333, | |
| "air_bench_scorer/air_15_4142_28": 0.9333333333333333, | |
| "air_bench_scorer/air_15_4142_29": 0.9666666666666667, | |
| "air_bench_scorer/air_15_4142_30": 0.9333333333333333, | |
| "air_bench_scorer/air_15_4142_31": 0.9, | |
| "air_bench_scorer/air_15_4142_32": 0.8666666666666667, | |
| "air_bench_scorer/air_15_4142_33": 0.9333333333333333, | |
| "air_bench_scorer/air_15_4142_34": 1.0, | |
| "air_bench_scorer/air_15_4142_35": 0.8666666666666667, | |
| "air_bench_scorer/air_15_4142_36": 0.6944444444444444, | |
| "air_bench_scorer/air_15_4142_37": 0.8611111111111112, | |
| "air_bench_scorer/air_15_4142_38": 0.8, | |
| "air_bench_scorer/air_15_4142_39": 0.8611111111111112, | |
| "air_bench_scorer/air_15_4142_40": 0.4523809523809524, | |
| "air_bench_scorer/air_15_4142_41": 0.4, | |
| "air_bench_scorer/air_15_4142_42": 0.3333333333333333, | |
| "air_bench_scorer/air_15_4142_43": 0.26666666666666666, | |
| "air_bench_scorer/air_15_4142_44": 0.16666666666666666, | |
| "air_bench_scorer/air_15_4142_45": 0.4, | |
| "air_bench_scorer/air_15_4142_46": 0.4666666666666667, | |
| "air_bench_scorer/air_15_4142_47": 0.26666666666666666, | |
| "air_bench_scorer/air_15_4142_48": 0.4, | |
| "air_bench_scorer/air_15_4142_49": 0.2222222222222222, | |
| "air_bench_scorer/air_15_4142_50": 0.4666666666666667, | |
| "air_bench_scorer/air_15_4142_51": 0.9523809523809523, | |
| "air_bench_scorer/air_15_4142_52": 0.6666666666666666, | |
| "air_bench_scorer/air_15_4142_53": 0.4722222222222222, | |
| "air_bench_scorer/air_15_4142_54": 0.16666666666666666, | |
| "air_bench_scorer/air_15_4142_55": 0.9333333333333333, | |
| "air_bench_scorer/air_15_4142_56": 0.6666666666666666, | |
| "air_bench_scorer/air_15_4142_57": 0.8333333333333334, | |
| "air_bench_scorer/air_15_4142_58": 0.9333333333333333, | |
| "air_bench_scorer/air_15_4142_59": 0.8666666666666667, | |
| "air_bench_scorer/air_15_4142_60": 0.9166666666666666, | |
| "air_bench_scorer/air_15_4142_61": 0.9444444444444444, | |
| "air_bench_scorer/air_15_4142_62": 0.9444444444444444, | |
| "air_bench_scorer/air_15_4142_63": 0.9166666666666666, | |
| "air_bench_scorer/air_15_4142_64": 0.6666666666666666, | |
| "air_bench_scorer/air_15_4142_65": 0.3333333333333333, | |
| "air_bench_scorer/air_15_4142_66": 0.7222222222222222, | |
| "air_bench_scorer/air_15_4142_67": 0.6666666666666666, | |
| "air_bench_scorer/air_15_4142_68": 0.5666666666666667, | |
| "air_bench_scorer/air_15_4142_69": 0.16666666666666666, | |
| "air_bench_scorer/air_15_4142_70": 0.4666666666666667, | |
| "air_bench_scorer/air_15_4142_71": 0.5666666666666667, | |
| "air_bench_scorer/air_15_4142_72": 0.4523809523809524, | |
| "air_bench_scorer/air_16": 0.8, | |
| "air_bench_scorer/air_16_43": 0.8666666666666667, | |
| "air_bench_scorer/air_16_43_1": 0.8666666666666667, | |
| "air_bench_scorer/air_16_44": 0.6888888888888889, | |
| "air_bench_scorer/air_16_44_2": 0.5333333333333333, | |
| "air_bench_scorer/air_16_44_3": 0.8666666666666667, | |
| "air_bench_scorer/air_16_44_4": 0.6666666666666666, | |
| "air_bench_scorer/air_16_45": 0.8666666666666667, | |
| "air_bench_scorer/air_16_45_5": 0.8666666666666667, | |
| "air_bench_scorer/air_16_45_6": 0.9333333333333333, | |
| "air_bench_scorer/air_16_45_7": 0.8666666666666667, | |
| "air_bench_scorer/air_16_45_8": 0.8, | |
| "air_bench_scorer/all": 0.7126975763962066 | |
| }, | |
| "primary_metric": "air_bench_scorer/air_1", | |
| "primary_value": 0.7882882882882883 | |
| }, | |
| { | |
| "task": "arc_easy", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-13T00-26-39+00-00_arc-easy_VsHRq5U4CxiXQFZMqn8orN.eval", | |
| "n_samples": 2376, | |
| "metrics": { | |
| "choice/accuracy": 0.9595959595959596, | |
| "choice/stderr": 0.00404040404040404 | |
| }, | |
| "primary_metric": "choice/accuracy", | |
| "primary_value": 0.9595959595959596 | |
| }, | |
| { | |
| "task": "arc_challenge", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-13T00-28-31+00-00_arc-challenge_5VvcAGF33mvKvFqwRpPUr8.eval", | |
| "n_samples": 1172, | |
| "metrics": { | |
| "choice/accuracy": 0.8984641638225256, | |
| "choice/stderr": 0.008826359391637431 | |
| }, | |
| "primary_metric": "choice/accuracy", | |
| "primary_value": 0.8984641638225256 | |
| }, | |
| { | |
| "task": "assistant_bench_closed_book_zero_shot", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-13T00-29-32+00-00_assistant-bench-closed-book-zero-shot_AHiLMTGy98VQK5gppawn69.eval", | |
| "n_samples": 33, | |
| "metrics": { | |
| "assistant_bench_scorer/assistant_bench_accuracy": 0.16935344275592962, | |
| "assistant_bench_scorer/answer_rate": 0.9696969696969697 | |
| }, | |
| "primary_metric": "assistant_bench_scorer/assistant_bench_accuracy", | |
| "primary_value": 0.16935344275592962 | |
| }, | |
| { | |
| "task": "assistant_bench_closed_book_one_shot", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-13T00-30-03+00-00_assistant-bench-closed-book-one-shot_jmBNXuciNpRCZk7zSWNpd3.eval", | |
| "n_samples": 33, | |
| "metrics": { | |
| "assistant_bench_scorer/assistant_bench_accuracy": 0.2182594830561885, | |
| "assistant_bench_scorer/answer_rate": 0.9393939393939394 | |
| }, | |
| "primary_metric": "assistant_bench_scorer/assistant_bench_accuracy", | |
| "primary_value": 0.2182594830561885 | |
| }, | |
| { | |
| "task": "bbeh", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-13T00-30-47+00-00_bbeh_TiWfUJuAiYwq75Poebe9Qh.eval", | |
| "n_samples": 4519, | |
| "metrics": { | |
| "bbeh_scorer/sportqa": 0.015, | |
| "bbeh_scorer/zebra puzzles": 0.2, | |
| "bbeh_scorer/boardgame qa": 0.31, | |
| "bbeh_scorer/web of lies": 0.035, | |
| "bbeh_scorer/causal understanding": 0.245, | |
| "bbeh_scorer/disambiguation qa": 0.35, | |
| "bbeh_scorer/spatial reasoning": 0.0, | |
| "bbeh_scorer/linguini": 0.035, | |
| "bbeh_scorer/boolean expressions": 0.16, | |
| "bbeh_scorer/dyck languages": 0.005, | |
| "bbeh_scorer/shuffled objects": 0.07, | |
| "bbeh_scorer/object counting": 0.005, | |
| "bbeh_scorer/object properties": 0.0, | |
| "bbeh_scorer/movie recommendation": 0.28, | |
| "bbeh_scorer/geometric shapes": 0.35, | |
| "bbeh_scorer/temporal sequence": 0.025, | |
| "bbeh_scorer/hyperbaton": 0.015, | |
| "bbeh_scorer/multistep arithmetic": 0.0, | |
| "bbeh_scorer/buggy tables": 0.005, | |
| "bbeh_scorer/word sorting": 0.03, | |
| "bbeh_scorer/time arithmetic": 0.165, | |
| "bbeh_scorer/nycc": 0.125, | |
| "bbeh_scorer/sarc triples": 0.205, | |
| "bbeh_scorer/harmonic_mean_across_tasks": 0.03129322433260093 | |
| }, | |
| "primary_metric": "bbeh_scorer/sportqa", | |
| "primary_value": 0.015 | |
| }, | |
| { | |
| "task": "bbh", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-13T05-50-16+00-00_bbh_7BjQ2fJ9KdMb72YsnZvAiX.eval", | |
| "n_samples": 6509, | |
| "metrics": { | |
| "bbh_scorer/date_understanding": 0.544, | |
| "bbh_scorer/disambiguation_qa": 0.592, | |
| "bbh_scorer/geometric_shapes": 0.476, | |
| "bbh_scorer/hyperbaton": 0.604, | |
| "bbh_scorer/logical_deduction_five_objects": 0.492, | |
| "bbh_scorer/logical_deduction_seven_objects": 0.476, | |
| "bbh_scorer/logical_deduction_three_objects": 0.72, | |
| "bbh_scorer/movie_recommendation": 0.64, | |
| "bbh_scorer/penguins_in_a_table": 0.541095890410959, | |
| "bbh_scorer/reasoning_about_colored_objects": 0.6, | |
| "bbh_scorer/ruin_names": 0.6088709677419355, | |
| "bbh_scorer/salient_translation_error_detection": 0.504, | |
| "bbh_scorer/snarks": 0.6123595505617978, | |
| "bbh_scorer/temporal_sequences": 0.5, | |
| "bbh_scorer/tracking_shuffled_objects_five_objects": 0.224, | |
| "bbh_scorer/tracking_shuffled_objects_seven_objects": 0.148, | |
| "bbh_scorer/tracking_shuffled_objects_three_objects": 0.38, | |
| "bbh_scorer/boolean_expressions": 0.796, | |
| "bbh_scorer/causal_judgement": 0.5561497326203209, | |
| "bbh_scorer/formal_fallacies": 0.612, | |
| "bbh_scorer/navigate": 0.692, | |
| "bbh_scorer/sports_understanding": 0.744, | |
| "bbh_scorer/web_of_lies": 0.496, | |
| "bbh_scorer/multistep_arithmetic_two": 0.048, | |
| "bbh_scorer/object_counting": 0.384, | |
| "bbh_scorer/word_sorting": 0.188, | |
| "bbh_scorer/dyck_languages": 1.0, | |
| "bbh_scorer/all": 0.5235827316023967, | |
| "bbh_scorer/stderr": 0.006191026065576531 | |
| }, | |
| "primary_metric": "bbh_scorer/date_understanding", | |
| "primary_value": 0.544 | |
| }, | |
| { | |
| "task": "bbq", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-13T06-08-01+00-00_bbq_5DdjyMHccjZCUmtykU5S3N.eval", | |
| "n_samples": 58492, | |
| "metrics": { | |
| "choice/accuracy": 0.9181255556315393, | |
| "choice/stderr": 0.0011336544513365057 | |
| }, | |
| "primary_metric": "choice/accuracy", | |
| "primary_value": 0.9181255556315393 | |
| }, | |
| { | |
| "task": "bfcl", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-13T06-41-24+00-00_bfcl_kLdXcc6W9mvuqv8GSd2Ff3.eval", | |
| "n_samples": 3981, | |
| "metrics": { | |
| "bfcl_scorer/accuracy": 0.7382567194172318, | |
| "bfcl_scorer/stderr": 0.0069678683872793435, | |
| "bfcl_scorer/live_irrelevance_acc": 0.7217194570135747, | |
| "bfcl_scorer/parallel_multiple_acc": 0.84, | |
| "bfcl_scorer/simple_java_acc": 0.35, | |
| "bfcl_scorer/live_multiple_acc": 0.7056030389363722, | |
| "bfcl_scorer/multiple_acc": 0.94, | |
| "bfcl_scorer/simple_python_acc": 0.9475, | |
| "bfcl_scorer/sql_acc": 0.28, | |
| "bfcl_scorer/parallel_acc": 0.905, | |
| "bfcl_scorer/irrelevance_acc": 0.6083333333333333, | |
| "bfcl_scorer/live_simple_acc": 0.6744186046511628, | |
| "bfcl_scorer/exec_simple_acc": 0.94, | |
| "bfcl_scorer/live_relevance_acc": 0.75, | |
| "bfcl_scorer/simple_javascript_acc": 0.34, | |
| "bfcl_scorer/exec_parallel_acc": 0.8, | |
| "bfcl_scorer/exec_multiple_acc": 0.84, | |
| "bfcl_scorer/live_parallel_multiple_acc": 0.6666666666666666, | |
| "bfcl_scorer/exec_parallel_multiple_acc": 0.725, | |
| "bfcl_scorer/live_parallel_acc": 0.5625, | |
| "bfcl_scorer/all": 0.7382567194172318, | |
| "bfcl_scorer/live_irrelevance_sterr": 0.015081525616734058, | |
| "bfcl_scorer/parallel_multiple_sterr": 0.025988014245457665, | |
| "bfcl_scorer/simple_java_sterr": 0.047937248544110224, | |
| "bfcl_scorer/live_multiple_sterr": 0.014052028200906003, | |
| "bfcl_scorer/multiple_sterr": 0.016834995854681276, | |
| "bfcl_scorer/simple_python_sterr": 0.011165619222935151, | |
| "bfcl_scorer/sql_sterr": 0.04512608598542129, | |
| "bfcl_scorer/parallel_sterr": 0.02078545587374491, | |
| "bfcl_scorer/irrelevance_sterr": 0.03157404055853485, | |
| "bfcl_scorer/live_simple_sterr": 0.02922994509204248, | |
| "bfcl_scorer/exec_simple_sterr": 0.023868325657594204, | |
| "bfcl_scorer/live_relevance_sterr": 0.11180339887498948, | |
| "bfcl_scorer/simple_javascript_sterr": 0.0676726816132972, | |
| "bfcl_scorer/exec_parallel_sterr": 0.057142857142857134, | |
| "bfcl_scorer/exec_multiple_sterr": 0.05237229365663817, | |
| "bfcl_scorer/live_parallel_multiple_sterr": 0.09829463743659811, | |
| "bfcl_scorer/exec_parallel_multiple_sterr": 0.07149950690165274, | |
| "bfcl_scorer/live_parallel_sterr": 0.128086884574495, | |
| "bfcl_scorer/all2": 0.0069678683872793435 | |
| }, | |
| "primary_metric": "bfcl_scorer/accuracy", | |
| "primary_value": 0.7382567194172318 | |
| }, | |
| { | |
| "task": "boolq", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-13T07-30-23+00-00_boolq_FP9XfrWCg2WtWxzaanaXy5.eval", | |
| "n_samples": 3270, | |
| "metrics": { | |
| "pattern/accuracy": 0.8256880733944955, | |
| "pattern/stderr": 0.006635353989048526 | |
| }, | |
| "primary_metric": "pattern/accuracy", | |
| "primary_value": 0.8256880733944955 | |
| }, | |
| { | |
| "task": "coconot", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-13T11-36-58+00-00_coconot_jWUZTaHndcvxdvaX3HWnZT.eval", | |
| "n_samples": 1001, | |
| "metrics": { | |
| "model_graded_qa/Requests with safety concerns": 5.3164556962025316, | |
| "model_graded_qa/total": 5.4945054945054945, | |
| "model_graded_qa/Humanizing requests": 4.878048780487805, | |
| "model_graded_qa/Incomplete requests": 3.111111111111111, | |
| "model_graded_qa/Unsupported requests": 12.738853503184714, | |
| "model_graded_qa/Indeterminate requests": 2.112676056338028 | |
| }, | |
| "primary_metric": "model_graded_qa/Requests with safety concerns", | |
| "primary_value": 5.3164556962025316 | |
| }, | |
| { | |
| "task": "frontierscience", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-13T12-58-09+00-00_frontierscience_fJo9Botm5bvFMoPKjz73Kz.eval", | |
| "n_samples": 160, | |
| "metrics": { | |
| "model_graded_fact/accuracy": 0.04375, | |
| "model_graded_fact/stderr": 0.016220946451227344 | |
| }, | |
| "primary_metric": "model_graded_fact/accuracy", | |
| "primary_value": 0.04375 | |
| }, | |
| { | |
| "task": "agent_bench_os", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-19T18-44-44+00-00_agent-bench-os_ULLa7MqXw5soXhKiF5bi2Q.eval", | |
| "n_samples": 125, | |
| "metrics": { | |
| "agent_bench_os_default_scorer/accuracy": 0.112, | |
| "agent_bench_os_default_scorer/stderr": 0.02832074356596296 | |
| }, | |
| "primary_metric": "agent_bench_os_default_scorer/accuracy", | |
| "primary_value": 0.112 | |
| }, | |
| { | |
| "task": "aime2024", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-19T19-26-47+00-00_aime2024_LfA5NfujbK9L6pyAwcQCfc.eval", | |
| "n_samples": 30, | |
| "metrics": { | |
| "match/accuracy": 0.13333333333333333, | |
| "match/stderr": 0.06312427686319992 | |
| }, | |
| "primary_metric": "match/accuracy", | |
| "primary_value": 0.13333333333333333 | |
| }, | |
| { | |
| "task": "aime2025", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-19T19-28-25+00-00_aime2025_bckMgtLQrg7XBfhC5zUPx9.eval", | |
| "n_samples": 30, | |
| "metrics": { | |
| "aime_scorer/accuracy": 0.1, | |
| "aime_scorer/stderr": 0.055708601453115555 | |
| }, | |
| "primary_metric": "aime_scorer/accuracy", | |
| "primary_value": 0.1 | |
| }, | |
| { | |
| "task": "arc_easy", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-19T20-03-02+00-00_arc-easy_4bPtoaoRkNKETPn3dwhWGS.eval", | |
| "n_samples": 2376, | |
| "metrics": { | |
| "choice/accuracy": 0.9617003367003367, | |
| "choice/stderr": 0.003938089255666788 | |
| }, | |
| "primary_metric": "choice/accuracy", | |
| "primary_value": 0.9617003367003367 | |
| }, | |
| { | |
| "task": "arc_challenge", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-19T20-04-41+00-00_arc-challenge_ARsHRoDZuqUJU3HLETZPX4.eval", | |
| "n_samples": 1172, | |
| "metrics": { | |
| "choice/accuracy": 0.8993174061433447, | |
| "choice/stderr": 0.008793368024937355 | |
| }, | |
| "primary_metric": "choice/accuracy", | |
| "primary_value": 0.8993174061433447 | |
| }, | |
| { | |
| "task": "aime2024", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-20T01-57-07+00-00_aime2024_8Zu8nKRyFbyUPWzA8wpTnq.eval", | |
| "n_samples": 30, | |
| "metrics": { | |
| "match/accuracy": 0.13333333333333333, | |
| "match/stderr": 0.06312427686319992 | |
| }, | |
| "primary_metric": "match/accuracy", | |
| "primary_value": 0.13333333333333333 | |
| }, | |
| { | |
| "task": "aime2025", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-20T01-58-43+00-00_aime2025_UHbx293gStNSg4ej3WAZyC.eval", | |
| "n_samples": 30, | |
| "metrics": { | |
| "aime_scorer/accuracy": 0.06666666666666667, | |
| "aime_scorer/stderr": 0.04632055558531008 | |
| }, | |
| "primary_metric": "aime_scorer/accuracy", | |
| "primary_value": 0.06666666666666667 | |
| }, | |
| { | |
| "task": "air_bench", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-20T02-00-39+00-00_air-bench_XaLuCS9gAg3ryXTLzf6UF6.eval", | |
| "n_samples": 5694, | |
| "metrics": { | |
| "air_bench_scorer/air_1": 0.79, | |
| "air_bench_scorer/air_1_1": 0.79, | |
| "air_bench_scorer/air_1_1_1": 0.8888888888888888, | |
| "air_bench_scorer/air_1_1_2": 0.7222222222222222, | |
| "air_bench_scorer/air_1_1_3": 0.75, | |
| "air_bench_scorer/all": 0.79 | |
| }, | |
| "primary_metric": "air_bench_scorer/air_1", | |
| "primary_value": 0.79 | |
| }, | |
| { | |
| "task": "apps", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-20T02-02-00+00-00_apps_QiBThH9ZzQmusFU4HbYVZ9.eval", | |
| "n_samples": 3000, | |
| "metrics": { | |
| "verify/accuracy": 0.0, | |
| "verify/stderr": 0.0 | |
| }, | |
| "primary_metric": "verify/accuracy", | |
| "primary_value": 0.0 | |
| }, | |
| { | |
| "task": "arc_easy", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-20T02-02-51+00-00_arc-easy_UMx76jz8F5Xm4nq55qZeqx.eval", | |
| "n_samples": 2376, | |
| "metrics": { | |
| "choice/accuracy": 0.98, | |
| "choice/stderr": 0.019999999999999993 | |
| }, | |
| "primary_metric": "choice/accuracy", | |
| "primary_value": 0.98 | |
| }, | |
| { | |
| "task": "arc_challenge", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-20T02-03-05+00-00_arc-challenge_VddwJge9tVXCqJqkLXx9Qu.eval", | |
| "n_samples": 1172, | |
| "metrics": { | |
| "choice/accuracy": 0.9, | |
| "choice/stderr": 0.04285714285714286 | |
| }, | |
| "primary_metric": "choice/accuracy", | |
| "primary_value": 0.9 | |
| }, | |
| { | |
| "task": "bbeh", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-20T02-03-20+00-00_bbeh_T2egiqMhh4fA4NNMfjygA8.eval", | |
| "n_samples": 4519, | |
| "metrics": { | |
| "bbeh_scorer/sportqa": 0.0, | |
| "bbeh_scorer/zebra puzzles": 0.5, | |
| "bbeh_scorer/boardgame qa": 0.5, | |
| "bbeh_scorer/web of lies": 0.0, | |
| "bbeh_scorer/causal understanding": 0.2, | |
| "bbeh_scorer/disambiguation qa": 0.8333333333333334, | |
| "bbeh_scorer/spatial reasoning": 0.0, | |
| "bbeh_scorer/linguini": 0.0, | |
| "bbeh_scorer/boolean expressions": 0.0, | |
| "bbeh_scorer/dyck languages": 0.0, | |
| "bbeh_scorer/shuffled objects": 0.0, | |
| "bbeh_scorer/object counting": 0.0, | |
| "bbeh_scorer/object properties": 0.0, | |
| "bbeh_scorer/movie recommendation": 0.0, | |
| "bbeh_scorer/geometric shapes": 0.0, | |
| "bbeh_scorer/temporal sequence": 0.0, | |
| "bbeh_scorer/hyperbaton": 1.0, | |
| "bbeh_scorer/multistep arithmetic": 0.0, | |
| "bbeh_scorer/buggy tables": 0.0, | |
| "bbeh_scorer/word sorting": 0.0, | |
| "bbeh_scorer/time arithmetic": 0.0, | |
| "bbeh_scorer/harmonic_mean_across_tasks": 0.013036519972582938 | |
| }, | |
| "primary_metric": "bbeh_scorer/sportqa", | |
| "primary_value": 0.0 | |
| }, | |
| { | |
| "task": "bbh", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-20T02-09-14+00-00_bbh_GKS3WzfTtihjRjr5vL8rAM.eval", | |
| "n_samples": 6509, | |
| "metrics": { | |
| "bbh_scorer/date_understanding": 0.6, | |
| "bbh_scorer/all": 0.6, | |
| "bbh_scorer/stderr": 0.06998542122237651 | |
| }, | |
| "primary_metric": "bbh_scorer/date_understanding", | |
| "primary_value": 0.6 | |
| }, | |
| { | |
| "task": "bbq", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-20T02-09-38+00-00_bbq_P4hNv8kTkRVsrYQqj2wDVd.eval", | |
| "n_samples": 58492, | |
| "metrics": { | |
| "choice/accuracy": 0.6, | |
| "choice/stderr": 0.06998542122237651 | |
| }, | |
| "primary_metric": "choice/accuracy", | |
| "primary_value": 0.6 | |
| }, | |
| { | |
| "task": "bfcl", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-20T02-09-53+00-00_bfcl_54BdY8yRbXE5P3rydbFamm.eval", | |
| "n_samples": 3981, | |
| "metrics": { | |
| "bfcl_scorer/accuracy": 0.7, | |
| "bfcl_scorer/stderr": 0.06546536707079771, | |
| "bfcl_scorer/sql_acc": 0.0, | |
| "bfcl_scorer/live_irrelevance_acc": 0.8333333333333334, | |
| "bfcl_scorer/live_simple_acc": 1.0, | |
| "bfcl_scorer/live_multiple_acc": 0.2727272727272727, | |
| "bfcl_scorer/exec_multiple_acc": 0.0, | |
| "bfcl_scorer/irrelevance_acc": 0.6666666666666666, | |
| "bfcl_scorer/live_parallel_multiple_acc": 1.0, | |
| "bfcl_scorer/simple_javascript_acc": 1.0, | |
| "bfcl_scorer/simple_python_acc": 0.6666666666666666, | |
| "bfcl_scorer/exec_simple_acc": 1.0, | |
| "bfcl_scorer/simple_java_acc": 1.0, | |
| "bfcl_scorer/exec_parallel_multiple_acc": 1.0, | |
| "bfcl_scorer/parallel_multiple_acc": 1.0, | |
| "bfcl_scorer/parallel_acc": 1.0, | |
| "bfcl_scorer/all": 0.7, | |
| "bfcl_scorer/sql_sterr": 0.0, | |
| "bfcl_scorer/live_irrelevance_sterr": 0.0903876907577734, | |
| "bfcl_scorer/live_simple_sterr": 0.0, | |
| "bfcl_scorer/live_multiple_sterr": 0.14083575804390605, | |
| "bfcl_scorer/exec_multiple_sterr": 0.0, | |
| "bfcl_scorer/irrelevance_sterr": 0.33333333333333337, | |
| "bfcl_scorer/live_parallel_multiple_sterr": 0.0, | |
| "bfcl_scorer/simple_javascript_sterr": 0.0, | |
| "bfcl_scorer/simple_python_sterr": 0.33333333333333337, | |
| "bfcl_scorer/exec_simple_sterr": 0.0, | |
| "bfcl_scorer/simple_java_sterr": 0.0, | |
| "bfcl_scorer/exec_parallel_multiple_sterr": 0.0, | |
| "bfcl_scorer/parallel_multiple_sterr": 0.0, | |
| "bfcl_scorer/parallel_sterr": 0.0, | |
| "bfcl_scorer/all2": 0.06546536707079771 | |
| }, | |
| "primary_metric": "bfcl_scorer/accuracy", | |
| "primary_value": 0.7 | |
| }, | |
| { | |
| "task": "bold", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-20T02-11-04+00-00_bold_THqLo5HJKJz5LPFEN2X6gr.eval", | |
| "n_samples": 23679, | |
| "metrics": { | |
| "toxicity_scorer/gender": 0.0, | |
| "toxicity_scorer/all": 0.0, | |
| "toxicity_scorer/stderr": 0.0, | |
| "sentiment_scorer/gender": 0.72, | |
| "sentiment_scorer/all": 0.72, | |
| "sentiment_scorer/stderr": 0.08590455073355946, | |
| "regard_scorer/gender": 0.6, | |
| "regard_scorer/all": 0.6, | |
| "regard_scorer/stderr": 0.07559289460184544 | |
| }, | |
| "primary_metric": "toxicity_scorer/gender", | |
| "primary_value": 0.0 | |
| }, | |
| { | |
| "task": "boolq", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-20T02-11-36+00-00_boolq_fbP5tpukkxMy2KBnqTBB5o.eval", | |
| "n_samples": 3270, | |
| "metrics": { | |
| "pattern/accuracy": 0.82, | |
| "pattern/stderr": 0.0548839220351387 | |
| }, | |
| "primary_metric": "pattern/accuracy", | |
| "primary_value": 0.82 | |
| }, | |
| { | |
| "task": "chembench", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-20T02-11-53+00-00_chembench_maAA7hzyThVJJRxniRENqS.eval", | |
| "n_samples": 2785, | |
| "metrics": { | |
| "chembench_scorer/analytical_chemistry": 0.22, | |
| "chembench_scorer/all": 0.22, | |
| "chembench_scorer/stderr": 0.059178043363451366 | |
| }, | |
| "primary_metric": "chembench_scorer/analytical_chemistry", | |
| "primary_value": 0.22 | |
| }, | |
| { | |
| "task": "class_eval", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-20T02-12-09+00-00_class-eval_GqnZrNNWo3mXsuYJHXiJLy.eval", | |
| "n_samples": 100, | |
| "metrics": { | |
| "class_eval_scorer/mean": 0.84, | |
| "class_eval_scorer/std": 0.3703280399090206 | |
| }, | |
| "primary_metric": "class_eval_scorer/mean", | |
| "primary_value": 0.84 | |
| }, | |
| { | |
| "task": "commonsense_qa", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-20T02-14-17+00-00_commonsense-qa_FSZN4wFrHjgVhvnp4xAjsM.eval", | |
| "n_samples": 1221, | |
| "metrics": { | |
| "choice/accuracy": 0.78, | |
| "choice/stderr": 0.05917804336345136 | |
| }, | |
| "primary_metric": "choice/accuracy", | |
| "primary_value": 0.78 | |
| }, | |
| { | |
| "task": "compute_eval", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-20T02-15-52+00-00_compute-eval_RVn4YpyzwBzwCcuwM3T3Dk.eval", | |
| "n_samples": 406, | |
| "metrics": { | |
| "correctness_scorer/accuracy": 0.2, | |
| "correctness_scorer/stderr": 0.05714285714285715 | |
| }, | |
| "primary_metric": "correctness_scorer/accuracy", | |
| "primary_value": 0.2 | |
| }, | |
| { | |
| "task": "cybermetric_10000", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-20T02-29-33+00-00_cybermetric-10000_VwfY3bNywzvoND5NfbaHYs.eval", | |
| "n_samples": 10180, | |
| "metrics": { | |
| "choice/accuracy": 0.92, | |
| "choice/stderr": 0.03875617133214439 | |
| }, | |
| "primary_metric": "choice/accuracy", | |
| "primary_value": 0.92 | |
| }, | |
| { | |
| "task": "drop", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-20T02-29-49+00-00_drop_8sx8uKjRpYcLhiJhQkvdFC.eval", | |
| "n_samples": 9535, | |
| "metrics": { | |
| "f1/mean": 0.8370000000000001, | |
| "f1/stderr": 0.049153014149693794 | |
| }, | |
| "primary_metric": "f1/mean", | |
| "primary_value": 0.8370000000000001 | |
| }, | |
| { | |
| "task": "frontierscience", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-20T02-33-48+00-00_frontierscience_NGXhGvFRhwxYNmbSLcUFDg.eval", | |
| "n_samples": 160, | |
| "metrics": { | |
| "model_graded_fact/accuracy": 0.06, | |
| "model_graded_fact/stderr": 0.03392669167725119 | |
| }, | |
| "primary_metric": "model_graded_fact/accuracy", | |
| "primary_value": 0.06 | |
| }, | |
| { | |
| "task": "gaia", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-20T02-43-17+00-00_gaia_nM3zjaEB75bHeo42RvrjKC.eval", | |
| "n_samples": 165, | |
| "metrics": { | |
| "gaia_scorer/accuracy": 0.04, | |
| "gaia_scorer/stderr": 0.027994168488950612 | |
| }, | |
| "primary_metric": "gaia_scorer/accuracy", | |
| "primary_value": 0.04 | |
| }, | |
| { | |
| "task": "gpqa_diamond", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-20T04-28-16+00-00_gpqa-diamond_kghZr4Vw2SqJFkzPEQY4Zb.eval", | |
| "n_samples": 198, | |
| "metrics": { | |
| "choice/accuracy": 0.315, | |
| "choice/stderr": 0.04333660374890718 | |
| }, | |
| "primary_metric": "choice/accuracy", | |
| "primary_value": 0.315 | |
| }, | |
| { | |
| "task": "gsm8k", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-20T04-32-31+00-00_gsm8k_Do3cjBVYQvtoTAAjEABWAx.eval", | |
| "n_samples": 1319, | |
| "metrics": { | |
| "match/accuracy": 0.82, | |
| "match/stderr": 0.0548839220351387 | |
| }, | |
| "primary_metric": "match/accuracy", | |
| "primary_value": 0.82 | |
| }, | |
| { | |
| "task": "hellaswag", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-20T04-34-35+00-00_hellaswag_Qb986nKVi8oFZSPUrFroRC.eval", | |
| "n_samples": 10042, | |
| "metrics": { | |
| "choice/accuracy": 0.72, | |
| "choice/stderr": 0.06414269805898185 | |
| }, | |
| "primary_metric": "choice/accuracy", | |
| "primary_value": 0.72 | |
| }, | |
| { | |
| "task": "humaneval", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-20T04-35-03+00-00_humaneval_2zsfeveFbxFJJunFeciRjh.eval", | |
| "n_samples": 164, | |
| "metrics": { | |
| "verify/accuracy": 0.9, | |
| "verify/stderr": 0.04285714285714286 | |
| }, | |
| "primary_metric": "verify/accuracy", | |
| "primary_value": 0.9 | |
| }, | |
| { | |
| "task": "ifeval", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-20T04-35-43+00-00_ifeval_TezkUhejS82e35N9kQuF9V.eval", | |
| "n_samples": 541, | |
| "metrics": { | |
| "instruction_following/prompt_strict_acc": 0.68, | |
| "instruction_following/prompt_strict_stderr": 0.06663945022680344, | |
| "instruction_following/prompt_loose_acc": 0.72, | |
| "instruction_following/prompt_loose_stderr": 0.06414269805898185, | |
| "instruction_following/inst_strict_acc": 0.7368421052631579, | |
| "instruction_following/inst_strict_stderr": 0.05468149428348033, | |
| "instruction_following/inst_loose_acc": 0.7763157894736842, | |
| "instruction_following/inst_loose_stderr": 0.05207843530017688, | |
| "instruction_following/final_acc": 0.7282894736842105, | |
| "instruction_following/final_stderr": 0.06876950860162646 | |
| }, | |
| "primary_metric": "instruction_following/prompt_strict_acc", | |
| "primary_value": 0.68 | |
| }, | |
| { | |
| "task": "ifevalcode", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-20T04-38-40+00-00_ifevalcode_5g73e56qK7vvWhev8QUn44.eval", | |
| "n_samples": 810, | |
| "metrics": { | |
| "_ifevalcode_scorer/overall_accuracy": 0.0, | |
| "_ifevalcode_scorer/correctness": 0.04, | |
| "_ifevalcode_scorer/instruction_adherence": 0.02, | |
| "_ifevalcode_scorer/cpp_correctness": 0.04, | |
| "_ifevalcode_scorer/cpp_instruction": 0.02 | |
| }, | |
| "primary_metric": "_ifevalcode_scorer/overall_accuracy", | |
| "primary_value": 0.0 | |
| }, | |
| { | |
| "task": "lab_bench_litqa", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-20T04-42-15+00-00_lab-bench-litqa_i7ogQ2ifYyJS2ysMMDPW4D.eval", | |
| "n_samples": 199, | |
| "metrics": { | |
| "precision_choice/accuracy": 0.22, | |
| "precision_choice/precision": 0.4074074074074074, | |
| "precision_choice/coverage": 0.54, | |
| "precision_choice/stderr": 0.05917804336345138 | |
| }, | |
| "primary_metric": "precision_choice/accuracy", | |
| "primary_value": 0.22 | |
| }, | |
| { | |
| "task": "lab_bench_protocolqa", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-20T04-42-41+00-00_lab-bench-protocolqa_hrNNmXxBH9VzTtn6XzKg4w.eval", | |
| "n_samples": 108, | |
| "metrics": { | |
| "precision_choice/accuracy": 0.22, | |
| "precision_choice/precision": 0.3142857142857143, | |
| "precision_choice/coverage": 0.7, | |
| "precision_choice/stderr": 0.05917804336345138 | |
| }, | |
| "primary_metric": "precision_choice/accuracy", | |
| "primary_value": 0.22 | |
| }, | |
| { | |
| "task": "lab_bench_seqqa", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-20T04-43-09+00-00_lab-bench-seqqa_6YfTsSnFixQfVuPLyJoSiM.eval", | |
| "n_samples": 600, | |
| "metrics": { | |
| "precision_choice/accuracy": 0.28, | |
| "precision_choice/precision": 0.35, | |
| "precision_choice/coverage": 0.8, | |
| "precision_choice/stderr": 0.06414269805898185 | |
| }, | |
| "primary_metric": "precision_choice/accuracy", | |
| "primary_value": 0.28 | |
| }, | |
| { | |
| "task": "lab_bench_cloning_scenarios", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-20T04-43-34+00-00_lab-bench-cloning-scenarios_BqRwXQqRYPbXFrfjkNFfJV.eval", | |
| "n_samples": 33, | |
| "metrics": { | |
| "precision_choice/accuracy": 0.12121212121212122, | |
| "precision_choice/precision": 0.25, | |
| "precision_choice/coverage": 0.48484848484848486, | |
| "precision_choice/stderr": 0.057695250801999304 | |
| }, | |
| "primary_metric": "precision_choice/accuracy", | |
| "primary_value": 0.12121212121212122 | |
| }, | |
| { | |
| "task": "lingoly", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-20T04-44-17+00-00_lingoly_ac34mJtFRmtzFenAuer2yz.eval", | |
| "n_samples": 408, | |
| "metrics": { | |
| "exact_match_lingoly/no_context_delta": 0.015625, | |
| "exact_match_lingoly/no_context_mean": 0.0859375, | |
| "exact_match_lingoly/full_context_mean": 0.1015625 | |
| }, | |
| "primary_metric": "exact_match_lingoly/no_context_delta", | |
| "primary_value": 0.015625 | |
| }, | |
| { | |
| "task": "lingoly_too", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-20T04-45-13+00-00_lingoly-too_fJrfPpkk7pDoshzBnsyv2G.eval", | |
| "n_samples": 1203, | |
| "metrics": { | |
| "exact_match_lingoly_too/obfuscated_mean": 0.10195035460992906, | |
| "exact_match_lingoly_too/original_mean": 0.0, | |
| "exact_match_lingoly_too/stderr": 0.02463595486497009 | |
| }, | |
| "primary_metric": "exact_match_lingoly_too/obfuscated_mean", | |
| "primary_value": 0.10195035460992906 | |
| }, | |
| { | |
| "task": "coconot", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-20T11-49-57+00-00_coconot_dFPTxpF8PrhbAgZ3dmsoWP.eval", | |
| "n_samples": 1001, | |
| "metrics": { | |
| "model_graded_qa/Requests with safety concerns": 0.0, | |
| "model_graded_qa/total": 0.0 | |
| }, | |
| "primary_metric": "model_graded_qa/Requests with safety concerns", | |
| "primary_value": 0.0 | |
| }, | |
| { | |
| "task": "core_bench", | |
| "model": "hf/Qwen/Qwen2.5-7B-Instruct", | |
| "filename": "2026-03-20T11-51-12+00-00_core-bench_7btRV8PFgcM4ipC8L8TCb5.eval", | |
| "n_samples": 45, | |
| "metrics": { | |
| "evaluate_task_questions/accuracy": 0.0 | |
| }, | |
| "primary_metric": "evaluate_task_questions/accuracy", | |
| "primary_value": 0.0 | |
| } | |
| ] | |
| } |