{ "schema_version": 1, "accessed_at": "2026-11-07T18:40:28.918809Z", "zip_sha256": "3e15694c5985618bc1921e1de5c5ced2954a277b4a340a5766a79e92c59cc433", "generator_version": "0.1.0", "counts": { "kept_epoch": 28, "kept_upstream": 4, "dropped_licence": 5541, "dropped_model": 1782, "dropped_format": 0, "dropped_score": 0 }, "results": [ { "benchmark": "Chess Puzzles", "version": null, "model_id": "deepseek-v4.1-flash-1017", "model_version": "deepseek-v4.1-flash-1017_max", "score": { "value": 0.46, "unit": "fraction", "metric": "Best score (across scorers)" }, "evaluator": "Epoch AI", "agent": null, "scaffold": null, "run_date": "2026-10-19", "source": "https://epoch.ai/benchmarks", "source_url": "https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F4sRo7TxavQAsjaEALPZdDy.eval", "source_file": "chess_puzzles.csv", "run_id": "4sRo7TxavQAsjaEALPZdDy", "licence_id": "CC-BY-4.0", "licence_url": "https://creativecommons.org/licenses/by/4.0/", "licence_evidence_url": "https://epoch.ai/benchmarks?view=table", "attribution": "Source: Epoch AI, CC BY 4.0, accessed 2026-11-07. Adapted by RedRouter.", "epoch_attribution": null }, { "benchmark": "Chess Puzzles", "version": null, "model_id": "glm-5.3", "model_version": "glm-5.3_max", "score": { "value": 0.37, "unit": "fraction", "metric": "Best score (across scorers)" }, "evaluator": "Epoch AI", "agent": null, "scaffold": null, "run_date": "2026-10-13", "source": "https://epoch.ai/benchmarks", "source_url": "https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FkG3hbd8qLEd6fLAJHyQTiN.eval", "source_file": "chess_puzzles.csv", "run_id": "kG3hbd8qLEd6fLAJHyQTiN", "licence_id": "CC-BY-4.0", "licence_url": "https://creativecommons.org/licenses/by/4.0/", "licence_evidence_url": "https://epoch.ai/benchmarks?view=table", "attribution": "Source: Epoch AI, CC BY 4.0, accessed 2026-11-07. Adapted by RedRouter.", "epoch_attribution": null }, { "benchmark": "Chess Puzzles", "version": null, "model_id": "glm-5.3-flash", "model_version": "glm-5.3-flash_max", "score": { "value": 0.21, "unit": "fraction", "metric": "Best score (across scorers)" }, "evaluator": "Epoch AI", "agent": null, "scaffold": null, "run_date": "2026-10-13", "source": "https://epoch.ai/benchmarks", "source_url": "https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FfWNxmiSUC7BX8whqvzssY8.eval", "source_file": "chess_puzzles.csv", "run_id": "fWNxmiSUC7BX8whqvzssY8", "licence_id": "CC-BY-4.0", "licence_url": "https://creativecommons.org/licenses/by/4.0/", "licence_evidence_url": "https://epoch.ai/benchmarks?view=table", "attribution": "Source: Epoch AI, CC BY 4.0, accessed 2026-11-07. Adapted by RedRouter.", "epoch_attribution": null }, { "benchmark": "Chess Puzzles", "version": null, "model_id": "deepseek-v4.1-flash", "model_version": "deepseek-v4.1-flash_max", "score": { "value": 0.48, "unit": "fraction", "metric": "Best score (across scorers)" }, "evaluator": "Epoch AI", "agent": null, "scaffold": null, "run_date": "2026-10-13", "source": "https://epoch.ai/benchmarks", "source_url": "https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FACpDTbhRPwce2BWQTWD8iC.eval", "source_file": "chess_puzzles.csv", "run_id": "ACpDTbhRPwce2BWQTWD8iC", "licence_id": "CC-BY-4.0", "licence_url": "https://creativecommons.org/licenses/by/4.0/", "licence_evidence_url": "https://epoch.ai/benchmarks?view=table", "attribution": "Source: Epoch AI, CC BY 4.0, accessed 2026-11-07. Adapted by RedRouter.", "epoch_attribution": null }, { "benchmark": "FrontierMath-Tier-4-v2-Private", "version": null, "model_id": "deepseek-v4.1-flash-1017", "model_version": "deepseek-v4.1-flash-1017_max", "score": { "value": 0.4634146341463415, "unit": "fraction", "metric": "Best score (across scorers)" }, "evaluator": "Epoch AI", "agent": null, "scaffold": null, "run_date": "2026-10-19", "source": "https://epoch.ai/benchmarks", "source_url": "https://epoch.ai/benchmarks", "source_file": "frontiermath_tier_4_v2.csv", "run_id": "jnCfi6VttQBv3t54B3xp9G", "licence_id": "CC-BY-4.0", "licence_url": "https://creativecommons.org/licenses/by/4.0/", "licence_evidence_url": "https://epoch.ai/benchmarks?view=table", "attribution": "Source: Epoch AI, CC BY 4.0, accessed 2026-11-07. Adapted by RedRouter.", "epoch_attribution": null }, { "benchmark": "FrontierMath-Tier-4-v2-Private", "version": null, "model_id": "deepseek-v4.1-flash", "model_version": "deepseek-v4.1-flash_max", "score": { "value": 0.2682926829268293, "unit": "fraction", "metric": "Best score (across scorers)" }, "evaluator": "Epoch AI", "agent": null, "scaffold": null, "run_date": "2026-10-08", "source": "https://epoch.ai/benchmarks", "source_url": "https://epoch.ai/benchmarks", "source_file": "frontiermath_tier_4_v2.csv", "run_id": "KansJcyeGR4m7G4p8GupDn", "licence_id": "CC-BY-4.0", "licence_url": "https://creativecommons.org/licenses/by/4.0/", "licence_evidence_url": "https://epoch.ai/benchmarks?view=table", "attribution": "Source: Epoch AI, CC BY 4.0, accessed 2026-11-07. Adapted by RedRouter.", "epoch_attribution": null }, { "benchmark": "FrontierMath-Tier-4-v2-Private", "version": null, "model_id": "glm-5.3-flash", "model_version": "glm-5.3-flash_max", "score": { "value": 0.17073170731707318, "unit": "fraction", "metric": "Best score (across scorers)" }, "evaluator": "Epoch AI", "agent": null, "scaffold": null, "run_date": "2026-08-27", "source": "https://epoch.ai/benchmarks", "source_url": "https://epoch.ai/benchmarks", "source_file": "frontiermath_tier_4_v2.csv", "run_id": "iCysWvFJevNyw2dbYosU6J", "licence_id": "CC-BY-4.0", "licence_url": "https://creativecommons.org/licenses/by/4.0/", "licence_evidence_url": "https://epoch.ai/benchmarks?view=table", "attribution": "Source: Epoch AI, CC BY 4.0, accessed 2026-11-07. Adapted by RedRouter.", "epoch_attribution": null }, { "benchmark": "FrontierMath-Tier-4-v2-Private", "version": null, "model_id": "glm-5.3", "model_version": "glm-5.3_max", "score": { "value": 0.2926829268292683, "unit": "fraction", "metric": "Best score (across scorers)" }, "evaluator": "Epoch AI", "agent": null, "scaffold": null, "run_date": "2026-08-25", "source": "https://epoch.ai/benchmarks", "source_url": "https://epoch.ai/benchmarks", "source_file": "frontiermath_tier_4_v2.csv", "run_id": "4S3ZrJDkwh4gmGrmJQdvzR", "licence_id": "CC-BY-4.0", "licence_url": "https://creativecommons.org/licenses/by/4.0/", "licence_evidence_url": "https://epoch.ai/benchmarks?view=table", "attribution": "Source: Epoch AI, CC BY 4.0, accessed 2026-11-07. Adapted by RedRouter.", "epoch_attribution": null }, { "benchmark": "FrontierMath-Tiers-1-3-v2-Private", "version": null, "model_id": "deepseek-v4.1-flash-1017", "model_version": "deepseek-v4.1-flash-1017_max", "score": { "value": 0.712280701754386, "unit": "fraction", "metric": "Best score (across scorers)" }, "evaluator": "Epoch AI", "agent": null, "scaffold": null, "run_date": "2026-10-19", "source": "https://epoch.ai/benchmarks", "source_url": "https://epoch.ai/benchmarks", "source_file": "frontiermath_tiers_1_3_v2.csv", "run_id": "UnaMiD4Yy8W4WzyeSRwybr", "licence_id": "CC-BY-4.0", "licence_url": "https://creativecommons.org/licenses/by/4.0/", "licence_evidence_url": "https://epoch.ai/benchmarks?view=table", "attribution": "Source: Epoch AI, CC BY 4.0, accessed 2026-11-07. Adapted by RedRouter.", "epoch_attribution": null }, { "benchmark": "FrontierMath-Tiers-1-3-v2-Private", "version": null, "model_id": "deepseek-v4.1-flash", "model_version": "deepseek-v4.1-flash_max", "score": { "value": 0.6736842105263158, "unit": "fraction", "metric": "Best score (across scorers)" }, "evaluator": "Epoch AI", "agent": null, "scaffold": null, "run_date": "2026-10-08", "source": "https://epoch.ai/benchmarks", "source_url": "https://epoch.ai/benchmarks", "source_file": "frontiermath_tiers_1_3_v2.csv", "run_id": "b6dXtaGSwvfRYADKYnj9Ci", "licence_id": "CC-BY-4.0", "licence_url": "https://creativecommons.org/licenses/by/4.0/", "licence_evidence_url": "https://epoch.ai/benchmarks?view=table", "attribution": "Source: Epoch AI, CC BY 4.0, accessed 2026-11-07. Adapted by RedRouter.", "epoch_attribution": null }, { "benchmark": "FrontierMath-Tiers-1-3-v2-Private", "version": null, "model_id": "glm-5.3-flash", "model_version": "glm-5.3-flash_max", "score": { "value": 0.5578947368421052, "unit": "fraction", "metric": "Best score (across scorers)" }, "evaluator": "Epoch AI", "agent": null, "scaffold": null, "run_date": "2026-08-27", "source": "https://epoch.ai/benchmarks", "source_url": "https://epoch.ai/benchmarks", "source_file": "frontiermath_tiers_1_3_v2.csv", "run_id": "YC2u9wykbYQg4gdkf76j26", "licence_id": "CC-BY-4.0", "licence_url": "https://creativecommons.org/licenses/by/4.0/", "licence_evidence_url": "https://epoch.ai/benchmarks?view=table", "attribution": "Source: Epoch AI, CC BY 4.0, accessed 2026-11-07. Adapted by RedRouter.", "epoch_attribution": null }, { "benchmark": "FrontierMath-Tiers-1-3-v2-Private", "version": null, "model_id": "glm-5.3", "model_version": "glm-5.3_max", "score": { "value": 0.6877192982456141, "unit": "fraction", "metric": "Best score (across scorers)" }, "evaluator": "Epoch AI", "agent": null, "scaffold": null, "run_date": "2026-08-25", "source": "https://epoch.ai/benchmarks", "source_url": "https://epoch.ai/benchmarks", "source_file": "frontiermath_tiers_1_3_v2.csv", "run_id": "iXvqUzwxAiA3Rg3dwnutFs", "licence_id": "CC-BY-4.0", "licence_url": "https://creativecommons.org/licenses/by/4.0/", "licence_evidence_url": "https://epoch.ai/benchmarks?view=table", "attribution": "Source: Epoch AI, CC BY 4.0, accessed 2026-11-07. Adapted by RedRouter.", "epoch_attribution": null }, { "benchmark": "Furniture Assembly", "version": null, "model_id": "deepseek-v4.1-flash", "model_version": "deepseek-v4.1-flash_max", "score": { "value": 0.3416666666666667, "unit": "fraction", "metric": "Best score (across scorers)" }, "evaluator": "Epoch AI", "agent": null, "scaffold": null, "run_date": "2026-10-08", "source": "https://epoch.ai/benchmarks", "source_url": "https://epoch.ai/benchmarks", "source_file": "furniture_assembly.csv", "run_id": "JFQz7q3hxAKLV5pW6DmkGF", "licence_id": "CC-BY-4.0", "licence_url": "https://creativecommons.org/licenses/by/4.0/", "licence_evidence_url": "https://epoch.ai/benchmarks?view=table", "attribution": "Source: Epoch AI, CC BY 4.0, accessed 2026-11-07. Adapted by RedRouter.", "epoch_attribution": null }, { "benchmark": "GPQA diamond", "version": null, "model_id": "deepseek-v4.1-flash-1017", "model_version": "deepseek-v4.1-flash-1017_max", "score": { "value": 0.9318181818181818, "unit": "fraction", "metric": "Best score (across scorers)" }, "evaluator": "Epoch AI", "agent": null, "scaffold": null, "run_date": "2026-10-19", "source": "https://epoch.ai/benchmarks", "source_url": "https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FZK85PJtsCSeQJgV8dA4R4G.eval", "source_file": "gpqa_diamond.csv", "run_id": "ZK85PJtsCSeQJgV8dA4R4G", "licence_id": "CC-BY-4.0", "licence_url": "https://creativecommons.org/licenses/by/4.0/", "licence_evidence_url": "https://epoch.ai/benchmarks?view=table", "attribution": "Source: Epoch AI, CC BY 4.0, accessed 2026-11-07. Adapted by RedRouter.", "epoch_attribution": null }, { "benchmark": "GPQA diamond", "version": null, "model_id": "deepseek-v4.1-flash", "model_version": "deepseek-v4.1-flash_max", "score": { "value": 0.8983585858585859, "unit": "fraction", "metric": "Best score (across scorers)" }, "evaluator": "Epoch AI", "agent": null, "scaffold": null, "run_date": "2026-10-09", "source": "https://epoch.ai/benchmarks", "source_url": "https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FZU5ebpDaDPiDZLgv7cG8B9.eval", "source_file": "gpqa_diamond.csv", "run_id": "ZU5ebpDaDPiDZLgv7cG8B9", "licence_id": "CC-BY-4.0", "licence_url": "https://creativecommons.org/licenses/by/4.0/", "licence_evidence_url": "https://epoch.ai/benchmarks?view=table", "attribution": "Source: Epoch AI, CC BY 4.0, accessed 2026-11-07. Adapted by RedRouter.", "epoch_attribution": null }, { "benchmark": "GPQA diamond", "version": null, "model_id": "glm-5.3-flash", "model_version": "glm-5.3-flash_max", "score": { "value": 0.9015151515151515, "unit": "fraction", "metric": "Best score (across scorers)" }, "evaluator": "Epoch AI", "agent": null, "scaffold": null, "run_date": "2026-08-26", "source": "https://epoch.ai/benchmarks", "source_url": "https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FJvt5BNr4ERbE9QGgMcEbmT.eval", "source_file": "gpqa_diamond.csv", "run_id": "Jvt5BNr4ERbE9QGgMcEbmT", "licence_id": "CC-BY-4.0", "licence_url": "https://creativecommons.org/licenses/by/4.0/", "licence_evidence_url": "https://epoch.ai/benchmarks?view=table", "attribution": "Source: Epoch AI, CC BY 4.0, accessed 2026-11-07. Adapted by RedRouter.", "epoch_attribution": null }, { "benchmark": "GPQA diamond", "version": null, "model_id": "glm-5.3", "model_version": "glm-5.3_max", "score": { "value": 0.9090909090909091, "unit": "fraction", "metric": "Best score (across scorers)" }, "evaluator": "Epoch AI", "agent": null, "scaffold": null, "run_date": "2026-08-24", "source": "https://epoch.ai/benchmarks", "source_url": "https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FdLDBahYBTGRNjbsXA5pyr3.eval", "source_file": "gpqa_diamond.csv", "run_id": "dLDBahYBTGRNjbsXA5pyr3", "licence_id": "CC-BY-4.0", "licence_url": "https://creativecommons.org/licenses/by/4.0/", "licence_evidence_url": "https://epoch.ai/benchmarks?view=table", "attribution": "Source: Epoch AI, CC BY 4.0, accessed 2026-11-07. Adapted by RedRouter.", "epoch_attribution": null }, { "benchmark": "Mystery Game Puzzles", "version": null, "model_id": "deepseek-v4.1-flash-1017", "model_version": "deepseek-v4.1-flash-1017_max", "score": { "value": 0.49, "unit": "fraction", "metric": "Best score (across scorers)" }, "evaluator": "Epoch AI", "agent": null, "scaffold": null, "run_date": "2026-10-19", "source": "https://epoch.ai/benchmarks", "source_url": "https://epoch.ai/benchmarks", "source_file": "mystery_game_puzzles.csv", "run_id": "GLNTwoU6njn58DbPF9cbxb", "licence_id": "CC-BY-4.0", "licence_url": "https://creativecommons.org/licenses/by/4.0/", "licence_evidence_url": "https://epoch.ai/benchmarks?view=table", "attribution": "Source: Epoch AI, CC BY 4.0, accessed 2026-11-07. Adapted by RedRouter.", "epoch_attribution": null }, { "benchmark": "Mystery Game Puzzles", "version": null, "model_id": "deepseek-v4.1-flash", "model_version": "deepseek-v4.1-flash_max", "score": { "value": 0.43, "unit": "fraction", "metric": "Best score (across scorers)" }, "evaluator": "Epoch AI", "agent": null, "scaffold": null, "run_date": "2026-10-08", "source": "https://epoch.ai/benchmarks", "source_url": "https://epoch.ai/benchmarks", "source_file": "mystery_game_puzzles.csv", "run_id": "K3JABAsJCbXU5YrCPH2yVW", "licence_id": "CC-BY-4.0", "licence_url": "https://creativecommons.org/licenses/by/4.0/", "licence_evidence_url": "https://epoch.ai/benchmarks?view=table", "attribution": "Source: Epoch AI, CC BY 4.0, accessed 2026-11-07. Adapted by RedRouter.", "epoch_attribution": null }, { "benchmark": "Mystery Game Puzzles", "version": null, "model_id": "glm-5.3", "model_version": "glm-5.3_max", "score": { "value": 0.33, "unit": "fraction", "metric": "Best score (across scorers)" }, "evaluator": "Epoch AI", "agent": null, "scaffold": null, "run_date": "2026-08-30", "source": "https://epoch.ai/benchmarks", "source_url": "https://epoch.ai/benchmarks", "source_file": "mystery_game_puzzles.csv", "run_id": "UUq99Qhq3qizcoJo5vdhuK", "licence_id": "CC-BY-4.0", "licence_url": "https://creativecommons.org/licenses/by/4.0/", "licence_evidence_url": "https://epoch.ai/benchmarks?view=table", "attribution": "Source: Epoch AI, CC BY 4.0, accessed 2026-11-07. Adapted by RedRouter.", "epoch_attribution": null }, { "benchmark": "Mystery Game Puzzles", "version": null, "model_id": "glm-5.3-flash", "model_version": "glm-5.3-flash_max", "score": { "value": 0.08, "unit": "fraction", "metric": "Best score (across scorers)" }, "evaluator": "Epoch AI", "agent": null, "scaffold": null, "run_date": "2026-08-28", "source": "https://epoch.ai/benchmarks", "source_url": "https://epoch.ai/benchmarks", "source_file": "mystery_game_puzzles.csv", "run_id": "TMM3rPrAHcpBG5Pvw9kr4L", "licence_id": "CC-BY-4.0", "licence_url": "https://creativecommons.org/licenses/by/4.0/", "licence_evidence_url": "https://epoch.ai/benchmarks?view=table", "attribution": "Source: Epoch AI, CC BY 4.0, accessed 2026-11-07. Adapted by RedRouter.", "epoch_attribution": null }, { "benchmark": "OTIS Mock AIME 2024-2025", "version": null, "model_id": "deepseek-v4.1-flash-1017", "model_version": "deepseek-v4.1-flash-1017_max", "score": { "value": 0.9944444444444445, "unit": "fraction", "metric": "Best score (across scorers)" }, "evaluator": "Epoch AI", "agent": null, "scaffold": null, "run_date": "2026-10-19", "source": "https://epoch.ai/benchmarks", "source_url": "https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FchayEvHvpt2Wcif7pg64hF.eval", "source_file": "otis_mock_aime_2024_2025.csv", "run_id": "chayEvHvpt2Wcif7pg64hF", "licence_id": "CC-BY-4.0", "licence_url": "https://creativecommons.org/licenses/by/4.0/", "licence_evidence_url": "https://epoch.ai/benchmarks?view=table", "attribution": "Source: Epoch AI, CC BY 4.0, accessed 2026-11-07. Adapted by RedRouter.", "epoch_attribution": null }, { "benchmark": "OTIS Mock AIME 2024-2025", "version": null, "model_id": "deepseek-v4.1-flash", "model_version": "deepseek-v4.1-flash_max", "score": { "value": 0.9833333333333333, "unit": "fraction", "metric": "Best score (across scorers)" }, "evaluator": "Epoch AI", "agent": null, "scaffold": null, "run_date": "2026-10-08", "source": "https://epoch.ai/benchmarks", "source_url": "https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F7eHNiVQCzLcAyj5LxmeeSU.eval", "source_file": "otis_mock_aime_2024_2025.csv", "run_id": "7eHNiVQCzLcAyj5LxmeeSU", "licence_id": "CC-BY-4.0", "licence_url": "https://creativecommons.org/licenses/by/4.0/", "licence_evidence_url": "https://epoch.ai/benchmarks?view=table", "attribution": "Source: Epoch AI, CC BY 4.0, accessed 2026-11-07. Adapted by RedRouter.", "epoch_attribution": null }, { "benchmark": "OTIS Mock AIME 2024-2025", "version": null, "model_id": "glm-5.3-flash", "model_version": "glm-5.3-flash_max", "score": { "value": 0.9388888888888889, "unit": "fraction", "metric": "Best score (across scorers)" }, "evaluator": "Epoch AI", "agent": null, "scaffold": null, "run_date": "2026-08-26", "source": "https://epoch.ai/benchmarks", "source_url": "https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FNCikvVWc5SEyMEbCqvVNb2.eval", "source_file": "otis_mock_aime_2024_2025.csv", "run_id": "NCikvVWc5SEyMEbCqvVNb2", "licence_id": "CC-BY-4.0", "licence_url": "https://creativecommons.org/licenses/by/4.0/", "licence_evidence_url": "https://epoch.ai/benchmarks?view=table", "attribution": "Source: Epoch AI, CC BY 4.0, accessed 2026-11-07. Adapted by RedRouter.", "epoch_attribution": null }, { "benchmark": "OTIS Mock AIME 2024-2025", "version": null, "model_id": "glm-5.3", "model_version": "glm-5.3_max", "score": { "value": 0.9111111111111111, "unit": "fraction", "metric": "Best score (across scorers)" }, "evaluator": "Epoch AI", "agent": null, "scaffold": null, "run_date": "2026-08-24", "source": "https://epoch.ai/benchmarks", "source_url": "https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FgoZR5yGxZic9TZ23ezCL3w.eval", "source_file": "otis_mock_aime_2024_2025.csv", "run_id": "goZR5yGxZic9TZ23ezCL3w", "licence_id": "CC-BY-4.0", "licence_url": "https://creativecommons.org/licenses/by/4.0/", "licence_evidence_url": "https://epoch.ai/benchmarks?view=table", "attribution": "Source: Epoch AI, CC BY 4.0, accessed 2026-11-07. Adapted by RedRouter.", "epoch_attribution": null }, { "benchmark": "SimpleQA Verified", "version": null, "model_id": "deepseek-v4.1-flash-1017", "model_version": "deepseek-v4.1-flash-1017_max", "score": { "value": 0.425, "unit": "fraction", "metric": "Best score (across scorers)" }, "evaluator": "Epoch AI", "agent": null, "scaffold": null, "run_date": "2026-10-19", "source": "https://epoch.ai/benchmarks", "source_url": "https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FEi4XWaCH5drYUnDRo2MYCW.eval", "source_file": "simpleqa_verified.csv", "run_id": "Ei4XWaCH5drYUnDRo2MYCW", "licence_id": "CC-BY-4.0", "licence_url": "https://creativecommons.org/licenses/by/4.0/", "licence_evidence_url": "https://epoch.ai/benchmarks?view=table", "attribution": "Source: Epoch AI, CC BY 4.0, accessed 2026-11-07. Adapted by RedRouter.", "epoch_attribution": null }, { "benchmark": "SimpleQA Verified", "version": null, "model_id": "deepseek-v4.1-flash", "model_version": "deepseek-v4.1-flash_max", "score": { "value": 0.429, "unit": "fraction", "metric": "Best score (across scorers)" }, "evaluator": "Epoch AI", "agent": null, "scaffold": null, "run_date": "2026-10-13", "source": "https://epoch.ai/benchmarks", "source_url": "https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F3JJ4ChNxMo8CGAh3HrKNrw.eval", "source_file": "simpleqa_verified.csv", "run_id": "3JJ4ChNxMo8CGAh3HrKNrw", "licence_id": "CC-BY-4.0", "licence_url": "https://creativecommons.org/licenses/by/4.0/", "licence_evidence_url": "https://epoch.ai/benchmarks?view=table", "attribution": "Source: Epoch AI, CC BY 4.0, accessed 2026-11-07. Adapted by RedRouter.", "epoch_attribution": null }, { "benchmark": "SimpleQA Verified", "version": null, "model_id": "glm-5.3", "model_version": "glm-5.3_max", "score": { "value": 0.41, "unit": "fraction", "metric": "Best score (across scorers)" }, "evaluator": "Epoch AI", "agent": null, "scaffold": null, "run_date": "2026-08-28", "source": "https://epoch.ai/benchmarks", "source_url": "https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FTY8R8FV7zCwByEipkqyg2P.eval", "source_file": "simpleqa_verified.csv", "run_id": "TY8R8FV7zCwByEipkqyg2P", "licence_id": "CC-BY-4.0", "licence_url": "https://creativecommons.org/licenses/by/4.0/", "licence_evidence_url": "https://epoch.ai/benchmarks?view=table", "attribution": "Source: Epoch AI, CC BY 4.0, accessed 2026-11-07. Adapted by RedRouter.", "epoch_attribution": null }, { "benchmark": "WebDev Arena", "version": null, "model_id": "glm-5.3", "model_version": "glm-5.3_max", "score": { "value": 1614.45, "unit": "points", "metric": "Arena Score" }, "evaluator": "Arena (LMArena)", "agent": null, "scaffold": null, "run_date": null, "source": "https://arena.ai/leaderboard", "source_url": "https://arena.ai/leaderboard", "source_file": "webdev_arena_external.csv", "run_id": "recGUmCEUF1DKCZhV", "licence_id": "CC-BY-4.0", "licence_url": "https://creativecommons.org/licenses/by/4.0/", "licence_evidence_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/5a7e6bb84a93f55df56b198be8e56e53755a216a/README.md", "attribution": "Source: Arena (LMArena), CC BY 4.0, accessed 2026-11-07. Adapted by RedRouter.", "epoch_attribution": "Source: Epoch AI, CC BY 4.0, accessed 2026-11-07. Adapted by RedRouter." }, { "benchmark": "WebDev Arena", "version": null, "model_id": "deepseek-v4.1-flash", "model_version": "deepseek-v4.1-flash_max", "score": { "value": 1613.95, "unit": "points", "metric": "Arena Score" }, "evaluator": "Arena (LMArena)", "agent": null, "scaffold": null, "run_date": null, "source": "https://arena.ai/leaderboard", "source_url": "https://arena.ai/leaderboard", "source_file": "webdev_arena_external.csv", "run_id": "recUYd9mGJeTahnjd", "licence_id": "CC-BY-4.0", "licence_url": "https://creativecommons.org/licenses/by/4.0/", "licence_evidence_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/5a7e6bb84a93f55df56b198be8e56e53755a216a/README.md", "attribution": "Source: Arena (LMArena), CC BY 4.0, accessed 2026-11-07. Adapted by RedRouter.", "epoch_attribution": "Source: Epoch AI, CC BY 4.0, accessed 2026-11-07. Adapted by RedRouter." }, { "benchmark": "WebDev Arena", "version": null, "model_id": "glm-5.3-flash", "model_version": "glm-5.3-flash_unknown", "score": { "value": 1607.09, "unit": "points", "metric": "Arena Score" }, "evaluator": "Arena (LMArena)", "agent": null, "scaffold": null, "run_date": null, "source": "https://arena.ai/leaderboard", "source_url": "https://arena.ai/leaderboard", "source_file": "webdev_arena_external.csv", "run_id": "recnySn6GWU64r5vn", "licence_id": "CC-BY-4.0", "licence_url": "https://creativecommons.org/licenses/by/4.0/", "licence_evidence_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/5a7e6bb84a93f55df56b198be8e56e53755a216a/README.md", "attribution": "Source: Arena (LMArena), CC BY 4.0, accessed 2026-11-07. Adapted by RedRouter.", "epoch_attribution": "Source: Epoch AI, CC BY 4.0, accessed 2026-11-07. Adapted by RedRouter." }, { "benchmark": "WebDev Arena", "version": null, "model_id": "qwen3.8-27b", "model_version": "qwen3.8-27b", "score": { "value": 1593.29, "unit": "points", "metric": "Arena Score" }, "evaluator": "Arena (LMArena)", "agent": null, "scaffold": null, "run_date": null, "source": "https://arena.ai/leaderboard", "source_url": "https://arena.ai/leaderboard", "source_file": "webdev_arena_external.csv", "run_id": "rec67p0NIVtVh8Fw2", "licence_id": "CC-BY-4.0", "licence_url": "https://creativecommons.org/licenses/by/4.0/", "licence_evidence_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/5a7e6bb84a93f55df56b198be8e56e53755a216a/README.md", "attribution": "Source: Arena (LMArena), CC BY 4.0, accessed 2026-11-07. Adapted by RedRouter.", "epoch_attribution": "Source: Epoch AI, CC BY 4.0, accessed 2026-11-07. Adapted by RedRouter." } ] }