{ "eval_set_id": "P6eK8aWJ3VXXWRDvzbr7zK", "tasks": [ { "name": "aa_omniscience", "task_id": "QA2dSkk7LB6SLu2MuKu9T4", "task_args": { "lighteval_task_config": "aa_omniscience", "epochs": 1, "epochs_reducer": null }, "model": "hf-inference-providers/openai/gpt-oss-20b", "model_args": {}, "sequence": 0 }, { "name": "aa_omniscience", "task_id": "d9f4HJve7aW9u48LcggbZB", "task_args": { "lighteval_task_config": "aa_omniscience", "epochs": 1, "epochs_reducer": null }, "model": "hf-inference-providers/openai/gpt-oss-120b", "model_args": {}, "sequence": 0 }, { "name": "aa_omniscience", "task_id": "8CoDuPXNFtHVaAdjugJ7MW", "task_args": { "lighteval_task_config": "aa_omniscience", "epochs": 1, "epochs_reducer": null }, "model": "hf-inference-providers/moonshotai/Kimi-K2-Instruct-0905", "model_args": {}, "sequence": 0 }, { "name": "aa_omniscience", "task_id": "9EksTSk7Uo5DMnguoBdHoZ", "task_args": { "lighteval_task_config": "aa_omniscience", "epochs": 1, "epochs_reducer": null }, "model": "hf-inference-providers/meta-llama/Llama-3.1-8B-Instruct", "model_args": {}, "sequence": 0 }, { "name": "aa_omniscience", "task_id": "GqbbSMn64nSV9EQsYtnuER", "task_args": { "lighteval_task_config": "aa_omniscience", "epochs": 1, "epochs_reducer": null }, "model": "hf-inference-providers/MiniMaxAI/MiniMax-M2", "model_args": {}, "sequence": 0 }, { "name": "aa_omniscience", "task_id": "KeCEh4EsFNueGRBNEwPwra", "task_args": { "lighteval_task_config": "aa_omniscience", "epochs": 1, "epochs_reducer": null }, "model": "hf-inference-providers/Qwen/Qwen3-4B-Instruct-2507", "model_args": {}, "sequence": 0 }, { "name": "aa_omniscience", "task_id": "SF9nrxGFXwAFfqaEyevZ2g", "task_args": { "lighteval_task_config": "aa_omniscience", "epochs": 1, "epochs_reducer": null }, "model": "hf-inference-providers/moonshotai/Kimi-K2-Thinking", "model_args": {}, "sequence": 0 }, { "name": "aa_omniscience", "task_id": "GzFu97n3Ky5mGZs65jJQiv", "task_args": { "lighteval_task_config": "aa_omniscience", "epochs": 1, "epochs_reducer": null }, "model": "hf-inference-providers/deepseek-ai/DeepSeek-R1", "model_args": {}, "sequence": 0 }, { "name": "aa_omniscience", "task_id": "Nk2WgRY2BnUpbSBEu5xpRW", "task_args": { "lighteval_task_config": "aa_omniscience", "epochs": 1, "epochs_reducer": null }, "model": "hf-inference-providers/HuggingFaceTB/SmolLM3-3B", "model_args": {}, "sequence": 0 } ] }