{ "schema_version": 1, "kind": "research_leaderboard", "published_date": "2026-09-20", "source_repository": "CamoAiLab/InferenceNet-Leaderboard", "source_revision": "6ea7c5684664bfe5c6e3d282a5e28f68244acd9e", "dataset_revision": "59f9512a38e594528807744214a60ee00367434e", "task_list": "Selected_1000/1000_new.csv", "tasks_per_group": 1000, "groups": 13, "records": 13000, "model_aliases": 6, "paired_groups": 12, "independent_groups": 1, "paired_arms": [ "baseline", "deepagents" ], "official_parity_verified": false, "models": [ { "id": "gpt-5.6-sol", "name": "GPT-5.6 Sol", "arms": { "baseline": { "path": "results/gpt-5.6-sol/baseline", "metrics": { "perfect": { "count": 338, "denominator": 1000, "unknown": 445, "failure": 217, "score": 33.8, "profile": "local-paper-v1", "verification": "accepted_summary" }, "compilation_success": { "count": 557, "denominator": 1000, "unknown": 3, "failure": 440, "score": 55.7, "profile": "hf-leaderboard-v1", "verification": "archived_task_flags" }, "partial_replication": { "count": 430, "denominator": 1000, "unknown": 444, "failure": 126, "score": 43.0, "profile": "hf-leaderboard-v1", "verification": "archived_task_flags" }, "coefficient_direction": { "count": 537, "denominator": 1000, "unknown": 444, "failure": 19, "score": 53.7, "profile": "hf-leaderboard-v1", "verification": "archived_task_flags" }, "significance_level": { "count": 485, "denominator": 1000, "unknown": 444, "failure": 71, "score": 48.5, "profile": "hf-leaderboard-v1", "verification": "archived_task_flags" } }, "generated_at": "2026-09-13T17:49:16.537733+00:00", "complete": true, "harness": "none", "model_call_cap": 1, "task_unknown_count": null, "invalid_evidence_count": 0, "interruption_count": 3, "evidence_class": "amended_comparison" }, "deepagents": { "path": "results/gpt-5.6-sol/deepagents", "metrics": { "perfect": { "count": 518, "denominator": 1000, "unknown": 95, "failure": 387, "score": 51.8, "profile": "local-paper-v1", "verification": "accepted_summary" }, "compilation_success": { "count": 910, "denominator": 1000, "unknown": 10, "failure": 80, "score": 91.0, "profile": "hf-leaderboard-v1", "verification": "archived_task_flags" }, "partial_replication": { "count": 699, "denominator": 1000, "unknown": 92, "failure": 209, "score": 69.9, "profile": "hf-leaderboard-v1", "verification": "archived_task_flags" }, "coefficient_direction": { "count": 879, "denominator": 1000, "unknown": 92, "failure": 29, "score": 87.9, "profile": "hf-leaderboard-v1", "verification": "archived_task_flags" }, "significance_level": { "count": 787, "denominator": 1000, "unknown": 93, "failure": 120, "score": 78.7, "profile": "hf-leaderboard-v1", "verification": "archived_task_flags" } }, "generated_at": "2026-09-13T17:49:16.537733+00:00", "complete": true, "harness": "DeepAgents", "model_call_cap": 6, "task_unknown_count": null, "invalid_evidence_count": 0, "interruption_count": 10, "evidence_class": "amended_comparison" } } }, { "id": "claude-opus-4-8", "name": "Claude Opus 4.8", "arms": { "baseline": { "path": "results/claude-opus-4-8/baseline", "metrics": { "perfect": { "count": 184, "denominator": 1000, "unknown": 538, "failure": 278, "score": 18.4, "profile": "local-paper-v1", "verification": "accepted_summary" }, "compilation_success": { "count": 467, "denominator": 1000, "unknown": 0, "failure": 533, "score": 46.7, "profile": "hf-leaderboard-v1", "verification": "archived_task_flags" }, "partial_replication": { "count": 305, "denominator": 1000, "unknown": 537, "failure": 158, "score": 30.5, "profile": "hf-leaderboard-v1", "verification": "archived_task_flags" }, "coefficient_direction": { "count": 437, "denominator": 1000, "unknown": 537, "failure": 26, "score": 43.7, "profile": "hf-leaderboard-v1", "verification": "archived_task_flags" }, "significance_level": { "count": 370, "denominator": 1000, "unknown": 537, "failure": 93, "score": 37.0, "profile": "hf-leaderboard-v1", "verification": "archived_task_flags" } }, "generated_at": "2026-09-13T17:50:43.870921+00:00", "complete": true, "harness": "none", "model_call_cap": 1, "task_unknown_count": null, "invalid_evidence_count": 0, "interruption_count": 0, "evidence_class": "amended_comparison" }, "deepagents": { "path": "results/claude-opus-4-8/deepagents", "metrics": { "perfect": { "count": 392, "denominator": 1000, "unknown": 174, "failure": 434, "score": 39.2, "profile": "local-paper-v1", "verification": "accepted_summary" }, "compilation_success": { "count": 834, "denominator": 1000, "unknown": 4, "failure": 162, "score": 83.4, "profile": "hf-leaderboard-v1", "verification": "archived_task_flags" }, "partial_replication": { "count": 621, "denominator": 1000, "unknown": 170, "failure": 209, "score": 62.1, "profile": "hf-leaderboard-v1", "verification": "archived_task_flags" }, "coefficient_direction": { "count": 793, "denominator": 1000, "unknown": 170, "failure": 37, "score": 79.3, "profile": "hf-leaderboard-v1", "verification": "archived_task_flags" }, "significance_level": { "count": 696, "denominator": 1000, "unknown": 172, "failure": 132, "score": 69.6, "profile": "hf-leaderboard-v1", "verification": "archived_task_flags" } }, "generated_at": "2026-09-13T17:50:43.870921+00:00", "complete": true, "harness": "DeepAgents", "model_call_cap": 6, "task_unknown_count": null, "invalid_evidence_count": 0, "interruption_count": 4, "evidence_class": "amended_comparison" } } }, { "id": "kimi-k3", "name": "Kimi K3", "arms": { "baseline": { "path": "results/kimi-k3/baseline", "metrics": { "perfect": { "count": 230, "denominator": 1000, "unknown": 481, "failure": 289, "score": 23.0, "profile": "local-paper-v1", "verification": "archived_task_flags" }, "compilation_success": { "count": 526, "denominator": 1000, "unknown": 5, "failure": 469, "score": 52.6, "profile": "hf-leaderboard-v1", "verification": "archived_task_flags" }, "partial_replication": { "count": 366, "denominator": 1000, "unknown": 481, "failure": 153, "score": 36.6, "profile": "hf-leaderboard-v1", "verification": "archived_task_flags" }, "coefficient_direction": { "count": 494, "denominator": 1000, "unknown": 481, "failure": 25, "score": 49.4, "profile": "hf-leaderboard-v1", "verification": "archived_task_flags" }, "significance_level": { "count": 431, "denominator": 1000, "unknown": 481, "failure": 88, "score": 43.1, "profile": "hf-leaderboard-v1", "verification": "archived_task_flags" } }, "generated_at": "2026-09-16T15:28:00.953066+00:00", "complete": false, "harness": "none", "model_call_cap": 1, "task_unknown_count": 5, "invalid_evidence_count": 0, "interruption_count": null, "evidence_class": "amended_comparison" }, "deepagents": { "path": "results/kimi-k3/deepagents", "metrics": { "perfect": { "count": 390, "denominator": 1000, "unknown": 159, "failure": 451, "score": 39.0, "profile": "local-paper-v1", "verification": "archived_task_flags" }, "compilation_success": { "count": 867, "denominator": 1000, "unknown": 4, "failure": 129, "score": 86.7, "profile": "hf-leaderboard-v1", "verification": "archived_task_flags" }, "partial_replication": { "count": 635, "denominator": 1000, "unknown": 156, "failure": 209, "score": 63.5, "profile": "hf-leaderboard-v1", "verification": "archived_task_flags" }, "coefficient_direction": { "count": 804, "denominator": 1000, "unknown": 156, "failure": 40, "score": 80.4, "profile": "hf-leaderboard-v1", "verification": "archived_task_flags" }, "significance_level": { "count": 709, "denominator": 1000, "unknown": 157, "failure": 134, "score": 70.9, "profile": "hf-leaderboard-v1", "verification": "archived_task_flags" } }, "generated_at": "2026-09-16T15:28:00.953066+00:00", "complete": false, "harness": "DeepAgents 0.7.13", "model_call_cap": 6, "task_unknown_count": 4, "invalid_evidence_count": 0, "interruption_count": null, "evidence_class": "amended_comparison" } } }, { "id": "gemini-3.1-pro-preview", "name": "Gemini 3.1 Pro Preview", "arms": { "baseline": { "path": "results/gemini-3.1-pro-preview/baseline", "metrics": { "perfect": { "count": 246, "denominator": 1000, "unknown": 462, "failure": 292, "score": 24.6, "profile": "local-paper-v1", "verification": "archived_task_flags" }, "compilation_success": { "count": 543, "denominator": 1000, "unknown": 0, "failure": 457, "score": 54.3, "profile": "hf-leaderboard-v1", "verification": "archived_task_flags" }, "partial_replication": { "count": 366, "denominator": 1000, "unknown": 460, "failure": 174, "score": 36.6, "profile": "hf-leaderboard-v1", "verification": "archived_task_flags" }, "coefficient_direction": { "count": 506, "denominator": 1000, "unknown": 460, "failure": 34, "score": 50.6, "profile": "hf-leaderboard-v1", "verification": "archived_task_flags" }, "significance_level": { "count": 437, "denominator": 1000, "unknown": 460, "failure": 103, "score": 43.7, "profile": "hf-leaderboard-v1", "verification": "archived_task_flags" } }, "generated_at": "2026-09-16T15:28:00.953066+00:00", "complete": true, "harness": "none", "model_call_cap": 1, "task_unknown_count": 0, "invalid_evidence_count": 0, "interruption_count": null, "evidence_class": "amended_comparison" }, "deepagents": { "path": "results/gemini-3.1-pro-preview/deepagents", "metrics": { "perfect": { "count": 391, "denominator": 1000, "unknown": 155, "failure": 454, "score": 39.1, "profile": "local-paper-v1", "verification": "archived_task_flags" }, "compilation_success": { "count": 850, "denominator": 1000, "unknown": 0, "failure": 150, "score": 85.0, "profile": "hf-leaderboard-v1", "verification": "archived_task_flags" }, "partial_replication": { "count": 632, "denominator": 1000, "unknown": 153, "failure": 215, "score": 63.2, "profile": "hf-leaderboard-v1", "verification": "archived_task_flags" }, "coefficient_direction": { "count": 811, "denominator": 1000, "unknown": 153, "failure": 36, "score": 81.1, "profile": "hf-leaderboard-v1", "verification": "archived_task_flags" }, "significance_level": { "count": 718, "denominator": 1000, "unknown": 154, "failure": 128, "score": 71.8, "profile": "hf-leaderboard-v1", "verification": "archived_task_flags" } }, "generated_at": "2026-09-16T15:28:00.953066+00:00", "complete": true, "harness": "DeepAgents 0.7.13", "model_call_cap": 6, "task_unknown_count": 0, "invalid_evidence_count": 0, "interruption_count": null, "evidence_class": "amended_comparison" } } }, { "id": "qwen3.7-max", "name": "Qwen3.7-Max", "arms": { "baseline": { "path": "results/qwen3.7-max/baseline", "metrics": { "perfect": { "count": 198, "denominator": 1000, "unknown": 519, "failure": 283, "score": 19.8, "profile": "local-paper-v1", "verification": "archived_task_flags" }, "compilation_success": { "count": 486, "denominator": 1000, "unknown": 0, "failure": 514, "score": 48.6, "profile": "hf-leaderboard-v1", "verification": "archived_task_flags" }, "partial_replication": { "count": 315, "denominator": 1000, "unknown": 518, "failure": 167, "score": 31.5, "profile": "hf-leaderboard-v1", "verification": "archived_task_flags" }, "coefficient_direction": { "count": 454, "denominator": 1000, "unknown": 518, "failure": 28, "score": 45.4, "profile": "hf-leaderboard-v1", "verification": "archived_task_flags" }, "significance_level": { "count": 396, "denominator": 1000, "unknown": 518, "failure": 86, "score": 39.6, "profile": "hf-leaderboard-v1", "verification": "archived_task_flags" } }, "generated_at": "2026-09-16T17:18:47.373930+00:00", "complete": true, "harness": "none", "model_call_cap": 1, "task_unknown_count": 0, "invalid_evidence_count": 0, "interruption_count": null, "evidence_class": "amended_comparison" }, "deepagents": { "path": "results/qwen3.7-max/deepagents", "metrics": { "perfect": { "count": 248, "denominator": 1000, "unknown": 481, "failure": 271, "score": 24.8, "profile": "local-paper-v1", "verification": "archived_task_flags" }, "compilation_success": { "count": 523, "denominator": 1000, "unknown": 7, "failure": 470, "score": 52.3, "profile": "hf-leaderboard-v1", "verification": "archived_task_flags" }, "partial_replication": { "count": 379, "denominator": 1000, "unknown": 481, "failure": 140, "score": 37.9, "profile": "hf-leaderboard-v1", "verification": "archived_task_flags" }, "coefficient_direction": { "count": 488, "denominator": 1000, "unknown": 481, "failure": 31, "score": 48.8, "profile": "hf-leaderboard-v1", "verification": "archived_task_flags" }, "significance_level": { "count": 433, "denominator": 1000, "unknown": 481, "failure": 86, "score": 43.3, "profile": "hf-leaderboard-v1", "verification": "archived_task_flags" } }, "generated_at": "2026-09-16T17:18:47.373930+00:00", "complete": false, "harness": "DeepAgents 0.7.13", "model_call_cap": 6, "task_unknown_count": 6, "invalid_evidence_count": 1, "interruption_count": null, "evidence_class": "amended_comparison" } } }, { "id": "deepseek-v4-pro", "name": "DeepSeek V4 Pro", "arms": { "baseline": { "path": "results/deepseek-v4-pro/baseline", "metrics": { "perfect": { "count": 129, "denominator": 1000, "unknown": 723, "failure": 148, "score": 12.9, "profile": "local-paper-v1", "verification": "archived_task_flags" }, "compilation_success": { "count": 281, "denominator": 1000, "unknown": 0, "failure": 719, "score": 28.1, "profile": "hf-leaderboard-v1", "verification": "archived_task_flags" }, "partial_replication": { "count": 195, "denominator": 1000, "unknown": 723, "failure": 82, "score": 19.5, "profile": "hf-leaderboard-v1", "verification": "archived_task_flags" }, "coefficient_direction": { "count": 260, "denominator": 1000, "unknown": 723, "failure": 17, "score": 26.0, "profile": "hf-leaderboard-v1", "verification": "archived_task_flags" }, "significance_level": { "count": 236, "denominator": 1000, "unknown": 723, "failure": 41, "score": 23.6, "profile": "hf-leaderboard-v1", "verification": "archived_task_flags" } }, "generated_at": "2026-09-16T17:18:47.373930+00:00", "complete": true, "harness": "none", "model_call_cap": 1, "task_unknown_count": 0, "invalid_evidence_count": 0, "interruption_count": null, "evidence_class": "amended_comparison" }, "deepagents": { "path": "results/deepseek-v4-pro/deepagents", "metrics": { "perfect": { "count": 183, "denominator": 1000, "unknown": 648, "failure": 169, "score": 18.3, "profile": "local-paper-v1", "verification": "archived_task_flags" }, "compilation_success": { "count": 352, "denominator": 1000, "unknown": 0, "failure": 648, "score": 35.2, "profile": "hf-leaderboard-v1", "verification": "archived_task_flags" }, "partial_replication": { "count": 270, "denominator": 1000, "unknown": 648, "failure": 82, "score": 27.0, "profile": "hf-leaderboard-v1", "verification": "archived_task_flags" }, "coefficient_direction": { "count": 338, "denominator": 1000, "unknown": 648, "failure": 14, "score": 33.8, "profile": "hf-leaderboard-v1", "verification": "archived_task_flags" }, "significance_level": { "count": 308, "denominator": 1000, "unknown": 648, "failure": 44, "score": 30.8, "profile": "hf-leaderboard-v1", "verification": "archived_task_flags" } }, "generated_at": "2026-09-16T17:18:47.373930+00:00", "complete": true, "harness": "DeepAgents 0.7.13", "model_call_cap": 6, "task_unknown_count": 0, "invalid_evidence_count": 0, "interruption_count": null, "evidence_class": "amended_comparison" }, "dsh": { "path": "results/deepseek-v4-pro/dsh", "metrics": { "perfect": { "count": 372, "denominator": 1000, "unknown": 305, "failure": 323, "score": 37.2, "profile": "local-paper-v1", "verification": "archived_task_flags" }, "compilation_success": { "count": 699, "denominator": 1000, "unknown": 30, "failure": 271, "score": 69.9, "profile": "hf-leaderboard-v1", "verification": "archived_task_flags" }, "partial_replication": { "count": 556, "denominator": 1000, "unknown": 302, "failure": 142, "score": 55.6, "profile": "hf-leaderboard-v1", "verification": "archived_task_flags" }, "coefficient_direction": { "count": 683, "denominator": 1000, "unknown": 302, "failure": 15, "score": 68.3, "profile": "hf-leaderboard-v1", "verification": "archived_task_flags" }, "significance_level": { "count": 598, "denominator": 1000, "unknown": 304, "failure": 98, "score": 59.8, "profile": "hf-leaderboard-v1", "verification": "archived_task_flags" } }, "generated_at": "2026-09-19T18:18:48.070003+00:00", "complete": false, "harness": "DeepSeek Harness SDK 0.1.5rc1", "model_call_cap": 6, "task_unknown_count": 30, "invalid_evidence_count": 0, "interruption_count": null, "evidence_class": "technical_recovery_view", "display_name": "DeepSeek API [v4-pro alias] + DSH", "identity_notice": "Requested API alias: deepseek-v4-pro. Underlying model weights are unverified. This technical recovery result is a separate harness entry, not a paired DeepAgents gain.", "paired_comparison": false, "model_alias": "deepseek-v4-pro", "underlying_model_weights_verified": false, "comparison_group": "independent", "protocol_url": "results/deepseek-v4-pro/dsh/README.md" } } } ], "source_sha256": { "results/gpt-5.6-sol/baseline/summary.json": "6d6ab1aaffe754e08f9656dcb5f51fcd5c772e60660dc34d86cfc21f3c5c03d7", "results/gpt-5.6-sol/baseline/results.jsonl": "3b12160382043e27531ff5cb3e23bccc9a8f7807e4121a82ffa13df28f65a859", "results/gpt-5.6-sol/baseline/config.json": "90ec4e0781b57498fef52de31eacf5c8ec9424549643865a7140a1ccdb04c1d4", "results/gpt-5.6-sol/deepagents/summary.json": "821ca6e55a66006c7fb958951a7859a9dccde29d87de8415d5c3f07f523563c5", "results/gpt-5.6-sol/deepagents/results.jsonl": "378cdec8e7a880f091ba442649d1c034997acefdc623898b60a063baad29d7be", "results/gpt-5.6-sol/deepagents/config.json": "a3e24175f2395cffbbcd6d9d3c89689bd3a3b22dd4ce61bb78d5da33c6b6cc1b", "results/claude-opus-4-8/baseline/summary.json": "7b5b06bd9b3d7b47952b1dc424a01fcdf04ddccca0b3f64d04132358d6380cdc", "results/claude-opus-4-8/baseline/results.jsonl": "b9d6bd51c9eb81a634e78e422c86da16f655d97da87d3f5afa4c9aa0f96809f4", "results/claude-opus-4-8/baseline/config.json": "8058afcd14c34d666277c0f32ac5962398b10618df5b1aa0e13cd9862344dc56", "results/claude-opus-4-8/deepagents/summary.json": "f86da9c76f8becb75b4970c486160013209a6aa4239923018b217e55f1b0a614", "results/claude-opus-4-8/deepagents/results.jsonl": "3bef3b9850f24b9cb0b5806efd8425c4e4cc650735a6b28b45befdd55a6ec28a", "results/claude-opus-4-8/deepagents/config.json": "12215dfcba5d2d692268a305364514a03ff7579094b2d4af12f493383b8e0f21", "results/kimi-k3/baseline/summary.json": "2edd2e96f3b448ceceb6189edb7f23c737b245c00c9820728c69f5237feb34b7", "results/kimi-k3/baseline/results.jsonl": "0502ae8892dd6c66ee92890a83c678527cff6c3396aa4c13faaadcf41e1857c1", "results/kimi-k3/baseline/config.json": "7191c406e8695a5cb760ee8fa99c4fb0dd71bca59347acc4d6d33fe0630be081", "results/kimi-k3/deepagents/summary.json": "81c8cabaa58acc65ef6afba792241b70951b666ab90c3f7c25194b61b0d9a228", "results/kimi-k3/deepagents/results.jsonl": "bdab99f8f1d81885f74326cf9c8c8e57b9bb8a8d616bfbb1b5a2f6bf32b737ca", "results/kimi-k3/deepagents/config.json": "312c9260c01d5988878e4f2b88da55a16362ee994e8217c63b15ba772da3857c", "results/gemini-3.1-pro-preview/baseline/summary.json": "a8ba5100a28f1f0aeae6949eb3669c7717c844c4e2eee6fa42ded351aef6b5c7", "results/gemini-3.1-pro-preview/baseline/results.jsonl": "2f1e2019157d105efee7ba311a49eba99abe4a7b84f0a4b4e0ac174e2d56cdba", "results/gemini-3.1-pro-preview/baseline/config.json": "ff9884d2095695a1f40f5fc573982b9a49fd53d41dca2a6fc36d04dc81f10998", "results/gemini-3.1-pro-preview/deepagents/summary.json": "bf9ce721c94103f91b0ca576f717f4f5dca7cc9965601658a65fc6d2a15b7045", "results/gemini-3.1-pro-preview/deepagents/results.jsonl": "c2824f8277b283a6dd60118b6e6a0cb0419e4c8b9193de15a7bcf7aaaad24181", "results/gemini-3.1-pro-preview/deepagents/config.json": "f09d9d99d26328ae2f54e9173b22f69d68f7d7bb50c3cc5e352c996b98dd57f9", "results/qwen3.7-max/baseline/summary.json": "e506814d33789673fcd6b8e6869cdcbd52371cd3d0455ce53ae27e1098a52214", "results/qwen3.7-max/baseline/results.jsonl": "4924e929d67956f9deb6c319605042d09f40b12f7bd2f18baa0464b8f7c9851a", "results/qwen3.7-max/baseline/config.json": "9f553440e741863e82f32fec11470affe6f0dbffa03c668c647bd63d8f73227f", "results/qwen3.7-max/deepagents/summary.json": "a5dcb2297ccc31a921e3f4eeb025ed81a764e16556a12068733cfe3bfe0bdbe3", "results/qwen3.7-max/deepagents/results.jsonl": "e009f8c5c88b05896836330822afbda33af463c1f264f9adb9bbf5b094e61dfa", "results/qwen3.7-max/deepagents/config.json": "3862d438d381ca3e57b1bf68921ef01a8c38727902152ada2c6e1fcf7b70cc77", "results/deepseek-v4-pro/baseline/summary.json": "c51e4f1de78eba8f30e4a59276fb7821132cd103f0ae3f9d04c75c98344f2e34", "results/deepseek-v4-pro/baseline/results.jsonl": "7827218f6f18f39988e8c439f0c93cab611c04d158d8704aa50c9274cd438837", "results/deepseek-v4-pro/baseline/config.json": "4cef524f37a325029ea4ad325b163f72f9cf725f507f20cd76424d06e71e24ad", "results/deepseek-v4-pro/deepagents/summary.json": "231e4264b0403e12788136d01af465f86fe9ba3c3ab992510925a7ef4c2a40e9", "results/deepseek-v4-pro/deepagents/results.jsonl": "a006c8b0b80064295faeb3aa7395a2408f0208677853448816b361bf67e39bb6", "results/deepseek-v4-pro/deepagents/config.json": "400c28e4008d5241bf50bc71c2674861846d6b6d2e7da21f2a7602a60ecc0ae9", "results/deepseek-v4-pro/dsh/summary.json": "62936f76b1ca0de5e761d1ea1f894343695503ce934bf0213dc9fde1ea72a782", "results/deepseek-v4-pro/dsh/results.jsonl": "b12427d5f4476351e571e4b29f61e0463540a1701bec51e642753d717dbc1df2", "results/deepseek-v4-pro/dsh/config.json": "df322f13761e06dc78cb553c5dac347ce4361599937af4017a902c56a7df9d77" } }