| GPQA diamondKnowledge | 63.64%gpt-5.6-luna_none Epoch AI evaluation · epoch-run Run: 2026-08-07 · gpqa_diamond.csv Reported standard error: ±3.43 pp. This is not a 90% interval. Inspect source ↗CC BY 4.0 | none / Epoch Inspect | Epoch AI run ↗ |
|---|
| GPQA diamondKnowledge | 82.32%gpt-5.6-luna_low Epoch AI evaluation · epoch-run Run: 2026-08-07 · gpqa_diamond.csv Reported standard error: ±2.72 pp. This is not a 90% interval. Inspect source ↗CC BY 4.0 | low / Epoch Inspect | Epoch AI run ↗ |
|---|
| GPQA diamondKnowledge | 91.60%gpt-5.6-luna_max Epoch AI evaluation · epoch-run Run: 2026-07-09 · gpqa_diamond.csv Reported standard error: ±1.73 pp. This is not a 90% interval. Inspect source ↗CC BY 4.0 | max / Epoch Inspect | Epoch AI run ↗ |
|---|
| FrontierMath-Tiers-1-3-v2-PrivateReasoning | 39.65%gpt-5.6-luna_none Epoch AI evaluation · epoch-run Run: 2026-08-29 · frontiermath_tiers_1_3_v2.csv Reported standard error: ±2.90 pp. This is not a 90% interval. Inspect source ↗CC BY 4.0 | none / Epoch Inspect | Epoch AI run ↗ |
|---|
| FrontierMath-Tiers-1-3-v2-PrivateReasoning | 41.40%gpt-5.6-luna_low Epoch AI evaluation · epoch-run Run: 2026-08-29 · frontiermath_tiers_1_3_v2.csv Reported standard error: ±2.92 pp. This is not a 90% interval. Inspect source ↗CC BY 4.0 | low / Epoch Inspect | Epoch AI run ↗ |
|---|
| FrontierMath-Tiers-1-3-v2-PrivateReasoning | 82.11%gpt-5.6-luna_max Epoch AI evaluation · epoch-run Run: 2026-07-09 · frontiermath_tiers_1_3_v2.csv Reported standard error: ±2.27 pp. This is not a 90% interval. Inspect source ↗CC BY 4.0 | max / Epoch Inspect | Epoch AI run ↗ |
|---|
| FrontierMath-Tier-4-v2-PrivateReasoning | 60.98%gpt-5.6-luna_max Epoch AI evaluation · epoch-run Run: 2026-07-09 · frontiermath_tier_4_v2.csv Reported standard error: ±7.71 pp. This is not a 90% interval. Inspect source ↗CC BY 4.0 | max / Epoch Inspect | Epoch AI run ↗ |
|---|
| OTIS Mock AIME 2024-2025Reasoning | 40.00%gpt-5.6-luna_none Epoch AI evaluation · epoch-run Run: 2026-08-07 · otis_mock_aime_2024_2025.csv Reported standard error: ±7.39 pp. This is not a 90% interval. Inspect source ↗CC BY 4.0 | none / Epoch Inspect | Epoch AI run ↗ |
|---|
| OTIS Mock AIME 2024-2025Reasoning | 66.67%gpt-5.6-luna_low Epoch AI evaluation · epoch-run Run: 2026-08-07 · otis_mock_aime_2024_2025.csv Reported standard error: ±7.11 pp. This is not a 90% interval. Inspect source ↗CC BY 4.0 | low / Epoch Inspect | Epoch AI run ↗ |
|---|
| OTIS Mock AIME 2024-2025Reasoning | 98.33%gpt-5.6-luna_max Epoch AI evaluation · epoch-run Run: 2026-07-09 · otis_mock_aime_2024_2025.csv Reported standard error: ±1.17 pp. This is not a 90% interval. Inspect source ↗CC BY 4.0 | max / Epoch Inspect | Epoch AI run ↗ |
|---|
| SimpleQA VerifiedKnowledge | 41.00%gpt-5.6-luna_max Epoch AI evaluation · epoch-run Run: 2026-08-10 · simpleqa_verified.csv Reported standard error: ±1.56 pp. This is not a 90% interval. Inspect source ↗CC BY 4.0 | max / Epoch Inspect | Epoch AI run ↗ |
|---|
| Chess PuzzlesReasoning | 43.00%gpt-5.6-luna_max Epoch AI evaluation · epoch-run Run: 2026-10-13 · chess_puzzles.csv Reported standard error: ±4.98 pp. This is not a 90% interval. Inspect source ↗CC BY 4.0 | max / Epoch Inspect | Epoch AI run ↗ |
|---|
| Chess PuzzlesReasoning | 17.00%gpt-5.6-luna_low Epoch AI evaluation · epoch-run Run: 2026-10-13 · chess_puzzles.csv Reported standard error: ±3.78 pp. This is not a 90% interval. Inspect source ↗CC BY 4.0 | low / Epoch Inspect | Epoch AI run ↗ |
|---|
| Chess PuzzlesReasoning | 3.00%gpt-5.6-luna_none Epoch AI evaluation · epoch-run Run: 2026-10-13 · chess_puzzles.csv Reported standard error: ±1.71 pp. This is not a 90% interval. Inspect source ↗CC BY 4.0 | none / Epoch Inspect | Epoch AI run ↗ |
|---|
| Mystery Game PuzzlesReasoning | 20.00%gpt-5.6-luna_none Epoch AI evaluation · epoch-run Run: 2026-08-30 · mystery_game_puzzles.csv Reported standard error: ±4.02 pp. This is not a 90% interval. Inspect source ↗CC BY 4.0 | none / Epoch Inspect | Epoch AI run ↗ |
|---|
| Mystery Game PuzzlesReasoning | 12.00%gpt-5.6-luna_medium Epoch AI evaluation · epoch-run Run: 2026-08-27 · mystery_game_puzzles.csv Reported standard error: ±3.27 pp. This is not a 90% interval. Inspect source ↗CC BY 4.0 | medium / Epoch Inspect | Epoch AI run ↗ |
|---|
| Mystery Game PuzzlesReasoning | 17.00%gpt-5.6-luna_low Epoch AI evaluation · epoch-run Run: 2026-08-27 · mystery_game_puzzles.csv Reported standard error: ±3.78 pp. This is not a 90% interval. Inspect source ↗CC BY 4.0 | low / Epoch Inspect | Epoch AI run ↗ |
|---|
| Mystery Game PuzzlesReasoning | 21.00%gpt-5.6-luna_max Epoch AI evaluation · epoch-run Run: 2026-07-28 · mystery_game_puzzles.csv Reported standard error: ±4.09 pp. This is not a 90% interval. Inspect source ↗CC BY 4.0 | max / Epoch Inspect | Epoch AI run ↗ |
|---|
| ARC-AGIReasoning | 88.00%gpt-5.6-luna_max https://arcprize.org/leaderboard · external Run: Date not supplied · arc_agi_external.csv Inspect source ↗CC BY 4.0 | max / Not reported | External · via Epoch ↗ |
|---|
| ARC-AGIReasoning | 87.67%gpt-5.6-luna_xhigh https://arcprize.org/leaderboard · external Run: Date not supplied · arc_agi_external.csv Inspect source ↗CC BY 4.0 | xhigh / Not reported | External · via Epoch ↗ |
|---|
| ARC-AGIReasoning | 87.67%gpt-5.6-luna_xhigh https://arcprize.org/leaderboard · external Run: Date not supplied · arc_agi_external.csv Inspect source ↗CC BY 4.0 | xhigh / Not reported | External · via Epoch ↗ |
|---|
| ARC-AGIReasoning | 76.50%gpt-5.6-luna_high https://arcprize.org/leaderboard · external Run: Date not supplied · arc_agi_external.csv Inspect source ↗CC BY 4.0 | high / Not reported | External · via Epoch ↗ |
|---|
| ARC-AGIReasoning | 56.50%gpt-5.6-luna_medium https://arcprize.org/leaderboard · external Run: Date not supplied · arc_agi_external.csv Inspect source ↗CC BY 4.0 | medium / Not reported | External · via Epoch ↗ |
|---|
| ARC-AGIReasoning | 34.17%gpt-5.6-luna_low https://arcprize.org/leaderboard · external Run: Date not supplied · arc_agi_external.csv Inspect source ↗CC BY 4.0 | low / Not reported | External · via Epoch ↗ |
|---|
| BalrogAgents | 45.60%gpt-5.6-luna_max https://balrogai.com/ · external Run: Date not supplied · balrog_external.csv Inspect source ↗CC BY 4.0 | max / Not reported | External · via Epoch ↗ |
|---|
| SimpleBenchReasoning | 46.80%gpt-5.6-luna_unknown SimpleBench Leaderboard · external Run: Date not supplied · simplebench_external.csv Inspect source ↗CC BY 4.0 | unknown / Not reported | External · via Epoch ↗ |
|---|
| SimpleBenchReasoning | 46.80%gpt-5.6-luna_xhigh https://lmcouncil.ai/benchmarks · external Run: Date not supplied · simplebench_external.csv Inspect source ↗CC BY 4.0 | xhigh / Not reported | External · via Epoch ↗ |
|---|
| WeirdMLCoding | 60.86%gpt-5.6-luna_high https://htihle.github.io/weirdml.html · external Run: Date not supplied · weirdml_external.csv Reported standard error: ±0.02 pp. This is not a 90% interval. Inspect source ↗CC BY 4.0 | high / Not reported | External · via Epoch ↗ |
|---|
| APEX-AgentsAgents | 43.00%gpt-5.6-luna_unknown External result; evaluator not specified · external Run: Date not supplied · apex_agents_external.csv Inspect source ↗CC BY 4.0 | unknown / Not reported | External · via Epoch ↗ |
|---|
| ARC-AGI-2Reasoning | 59.54%gpt-5.6-luna_max External result; evaluator not specified · external Run: Date not supplied · arc_agi_2_external.csv Inspect source ↗CC BY 4.0 | max / Not reported | External · via Epoch ↗ |
|---|
| ARC-AGI-2Reasoning | 47.64%gpt-5.6-luna_xhigh External result; evaluator not specified · external Run: Date not supplied · arc_agi_2_external.csv Inspect source ↗CC BY 4.0 | xhigh / Not reported | External · via Epoch ↗ |
|---|
| ARC-AGI-2Reasoning | 47.64%gpt-5.6-luna_xhigh External result; evaluator not specified · external Run: Date not supplied · arc_agi_2_external.csv Inspect source ↗CC BY 4.0 | xhigh / Not reported | External · via Epoch ↗ |
|---|
| ARC-AGI-2Reasoning | 29.31%gpt-5.6-luna_high External result; evaluator not specified · external Run: Date not supplied · arc_agi_2_external.csv Inspect source ↗CC BY 4.0 | high / Not reported | External · via Epoch ↗ |
|---|
| ARC-AGI-2Reasoning | 7.36%gpt-5.6-luna_medium External result; evaluator not specified · external Run: Date not supplied · arc_agi_2_external.csv Inspect source ↗CC BY 4.0 | medium / Not reported | External · via Epoch ↗ |
|---|
| ARC-AGI-2Reasoning | 5.14%gpt-5.6-luna_low External result; evaluator not specified · external Run: Date not supplied · arc_agi_2_external.csv Inspect source ↗CC BY 4.0 | low / Not reported | External · via Epoch ↗ |
|---|
| CursorBenchOther | 35.90%gpt-5.6-luna_max https://cursor.com/cursorbench · external Run: Date not supplied · cursorbench_external.csv Inspect source ↗CC BY 4.0 | max / Not reported | External · via Epoch ↗ |
|---|
| CursorBenchOther | 33.00%gpt-5.6-luna_xhigh https://cursor.com/cursorbench · external Run: Date not supplied · cursorbench_external.csv Inspect source ↗CC BY 4.0 | xhigh / Not reported | External · via Epoch ↗ |
|---|
| CursorBenchOther | 29.40%gpt-5.6-luna_high https://cursor.com/cursorbench · external Run: Date not supplied · cursorbench_external.csv Inspect source ↗CC BY 4.0 | high / Not reported | External · via Epoch ↗ |
|---|
| CursorBenchOther | 22.20%gpt-5.6-luna_medium https://cursor.com/cursorbench · external Run: Date not supplied · cursorbench_external.csv Inspect source ↗CC BY 4.0 | medium / Not reported | External · via Epoch ↗ |
|---|
| CursorBenchOther | 16.00%gpt-5.6-luna_low https://cursor.com/cursorbench · external Run: Date not supplied · cursorbench_external.csv Inspect source ↗CC BY 4.0 | low / Not reported | External · via Epoch ↗ |
|---|
| CritPtOther | 20.57%gpt-5.6-luna_max External result; evaluator not specified · external Run: Date not supplied · critpt_external.csv Inspect source ↗CC BY 4.0 | max / Not reported | External · via Epoch ↗ |
|---|
| CritPtOther | 20.57%gpt-5.6-luna_xhigh External result; evaluator not specified · external Run: Date not supplied · critpt_external.csv Inspect source ↗CC BY 4.0 | xhigh / Not reported | External · via Epoch ↗ |
|---|
| CritPtOther | 16.57%gpt-5.6-luna_high External result; evaluator not specified · external Run: Date not supplied · critpt_external.csv Inspect source ↗CC BY 4.0 | high / Not reported | External · via Epoch ↗ |
|---|
| CritPtOther | 4.86%gpt-5.6-luna_medium External result; evaluator not specified · external Run: Date not supplied · critpt_external.csv Inspect source ↗CC BY 4.0 | medium / Not reported | External · via Epoch ↗ |
|---|
| CritPtOther | 2.57%gpt-5.6-luna_low External result; evaluator not specified · external Run: Date not supplied · critpt_external.csv Inspect source ↗CC BY 4.0 | low / Not reported | External · via Epoch ↗ |
|---|
| CritPtOther | 0.29%gpt-5.6-luna_none External result; evaluator not specified · external Run: Date not supplied · critpt_external.csv Inspect source ↗CC BY 4.0 | none / Not reported | External · via Epoch ↗ |
|---|
| Surface Evolver BenchOther | 61.88%gpt-5.6-luna_medium https://yhenon.github.io/surface-evolver-llm-eval/ · external Run: Date not supplied · surface_evolver_bench_external.csv Inspect source ↗CC BY 4.0 | medium / Not reported | External · via Epoch ↗ |
|---|
| DeepSWECoding | 67.19%gpt-5.6-luna_max https://deepswe.datacurve.ai/ · external Run: Date not supplied · deepswe_external.csv Inspect source ↗CC BY 4.0 | max / mini-swe-agent | External · via Epoch ↗ |
|---|
| DeepSWECoding | 56.86%gpt-5.6-luna_xhigh https://deepswe.datacurve.ai/ · external Run: Date not supplied · deepswe_external.csv Inspect source ↗CC BY 4.0 | xhigh / mini-swe-agent | External · via Epoch ↗ |
|---|
| DeepSWECoding | 44.25%gpt-5.6-luna_high https://deepswe.datacurve.ai/ · external Run: Date not supplied · deepswe_external.csv Inspect source ↗CC BY 4.0 | high / mini-swe-agent | External · via Epoch ↗ |
|---|
| DeepSWECoding | 11.28%gpt-5.6-luna_medium https://deepswe.datacurve.ai/ · external Run: Date not supplied · deepswe_external.csv Inspect source ↗CC BY 4.0 | medium / mini-swe-agent | External · via Epoch ↗ |
|---|
| DeepSWECoding | 1.55%gpt-5.6-luna_low https://deepswe.datacurve.ai/ · external Run: Date not supplied · deepswe_external.csv Inspect source ↗CC BY 4.0 | low / mini-swe-agent | External · via Epoch ↗ |
|---|
| ProofBenchReasoning | 60.00%gpt-5.6-luna_max https://www.vals.ai/benchmarks/proof_bench · external Run: Date not supplied · proofbench_external.csv Reported standard error: ±4.92 pp. This is not a 90% interval. ProofBench v1.1 re-grade (vals.ai, 2026-08-14): corrected Lean formalizations + hardened grader (rejects sorry/admit shortcuts, larger elaboration budgets). Not comparable to v1.0-era values. Updated 2026-08-18 after multi-agent verification. Inspect source ↗CC BY 4.0 | max / Not reported | External · via Epoch ↗ |
|---|
| FrontierCodeCoding | 39.81%gpt-5.6-luna_unknown https://cognition.com/frontiercode · external Run: Date not supplied · frontiercode_external.csv Inspect source ↗CC BY 4.0 | unknown / codex | External · via Epoch ↗ |
|---|
| LMCAReasoning | 48.54%gpt-5.6-luna_max https://conceptualreasoning.ai/lmca · external Run: Date not supplied · lmca_external.csv Inspect source ↗CC BY 4.0 | max / Not reported | External · via Epoch ↗ |
|---|
| LMCAReasoning | 48.54%gpt-5.6-luna_xhigh https://conceptualreasoning.ai/lmca · external Run: Date not supplied · lmca_external.csv Inspect source ↗CC BY 4.0 | xhigh / Not reported | External · via Epoch ↗ |
|---|
| LMCAReasoning | 47.38%gpt-5.6-luna_high https://conceptualreasoning.ai/lmca · external Run: Date not supplied · lmca_external.csv Inspect source ↗CC BY 4.0 | high / Not reported | External · via Epoch ↗ |
|---|
| LMCAReasoning | 44.25%gpt-5.6-luna_medium https://conceptualreasoning.ai/lmca · external Run: Date not supplied · lmca_external.csv Inspect source ↗CC BY 4.0 | medium / Not reported | External · via Epoch ↗ |
|---|
| LMCAReasoning | 43.79%gpt-5.6-luna_low https://conceptualreasoning.ai/lmca · external Run: Date not supplied · lmca_external.csv Inspect source ↗CC BY 4.0 | low / Not reported | External · via Epoch ↗ |
|---|
| LMCAReasoning | 41.40%gpt-5.6-luna_none https://conceptualreasoning.ai/lmca · external Run: Date not supplied · lmca_external.csv Inspect source ↗CC BY 4.0 | none / Not reported | External · via Epoch ↗ |
|---|
| DTBenchReasoning | 88.80%gpt-5.6-luna_max https://conceptualreasoning.ai/dtbench · external Run: Date not supplied · dtbench_external.csv Inspect source ↗CC BY 4.0 | max / Not reported | External · via Epoch ↗ |
|---|
| DTBenchReasoning | 89.07%gpt-5.6-luna_xhigh https://conceptualreasoning.ai/dtbench · external Run: Date not supplied · dtbench_external.csv Inspect source ↗CC BY 4.0 | xhigh / Not reported | External · via Epoch ↗ |
|---|
| DTBenchReasoning | 86.67%gpt-5.6-luna_high https://conceptualreasoning.ai/dtbench · external Run: Date not supplied · dtbench_external.csv Inspect source ↗CC BY 4.0 | high / Not reported | External · via Epoch ↗ |
|---|
| DTBenchReasoning | 83.20%gpt-5.6-luna_medium https://conceptualreasoning.ai/dtbench · external Run: Date not supplied · dtbench_external.csv Inspect source ↗CC BY 4.0 | medium / Not reported | External · via Epoch ↗ |
|---|
| DTBenchReasoning | 80.00%gpt-5.6-luna_low https://conceptualreasoning.ai/dtbench · external Run: Date not supplied · dtbench_external.csv Inspect source ↗CC BY 4.0 | low / Not reported | External · via Epoch ↗ |
|---|
| DTBenchReasoning | 69.25%gpt-5.6-luna_none https://conceptualreasoning.ai/dtbench · external Run: Date not supplied · dtbench_external.csv Inspect source ↗CC BY 4.0 | none / Not reported | External · via Epoch ↗ |
|---|
| Furniture AssemblyReasoning | 42.50%gpt-5.6-luna_max Epoch AI evaluation · epoch-run Run: 2026-09-10 · furniture_assembly.csv Reported standard error: ±6.38 pp. This is not a 90% interval. Inspect source ↗CC BY 4.0 | max / Epoch Inspect | Epoch AI run ↗ |
|---|
| GDP.pdfOther | 22.70%gpt-5.6-luna_unknown https://surgehq.ai/benchmarks/gdp-pdf · external Run: Date not supplied · gdp_pdf_external.csv Inspect source ↗CC BY 4.0 | unknown / Not reported | External · via Epoch ↗ |
|---|
| GDP.pdfOther | 22.70%gpt-5.6-luna_medium https://surgehq.ai/benchmarks/gdp-pdf · external Run: Date not supplied · gdp_pdf_external.csv Inspect source ↗CC BY 4.0 | medium / Not reported | External · via Epoch ↗ |
|---|
| WeirdML v3Coding | 9.34%gpt-5.6-luna_xhigh https://htihle.github.io/weirdml.html · external Run: Date not supplied · weirdml_v3_external.csv Inspect source ↗CC BY 4.0 | xhigh / codex_cli | External · via Epoch ↗ |
|---|
| Terminal-Bench 4.0Agents | 17.27%GPT-5.6 Luna · Codex · max Terminal-Bench public leaderboard · benchmark-publisher Run: 2026-06-26 · 4-0-0/51c6d76e-5baa-48c1-97b3-88656c620eef Published model + agent result; agents differ across models. Not a controlled model-only evaluation. Reported trials: 330. Source 95% accuracy interval half-width: 2.85 pp; this is not a DC Power interval. Inspect source ↗Attributed public leaderboard score facts · Terminal-Bench | max / Terminal-Bench 4.0 · Codex | Terminal-Bench ↗ |
|---|
| ARC-AGI-2 · semi-privateReasoning | 5.14%GPT-5.6 Luna (Low) ARC Prize official leaderboard · benchmark-publisher Run: Date not supplied · evaluations.json · v2_Semi_Private Reported benchmark cost: $0.07 per task. Different from the token-workload estimate. Semi-private split only. Provider-adapter and custom-scaffold families are kept separate. Identical effort names do not imply identical compute budgets. Inspect source ↗Public leaderboard facts · ARC Prize | low / ARC Prize leaderboard baseline | ARC Prize ↗ |
|---|
| ARC-AGI-2 · semi-privateReasoning | 7.36%GPT-5.6 Luna (Medium) ARC Prize official leaderboard · benchmark-publisher Run: Date not supplied · evaluations.json · v2_Semi_Private Reported benchmark cost: $0.11 per task. Different from the token-workload estimate. Semi-private split only. Provider-adapter and custom-scaffold families are kept separate. Identical effort names do not imply identical compute budgets. Inspect source ↗Public leaderboard facts · ARC Prize | medium / ARC Prize leaderboard baseline | ARC Prize ↗ |
|---|
| ARC-AGI-2 · semi-privateReasoning | 29.31%GPT-5.6 Luna (High) ARC Prize official leaderboard · benchmark-publisher Run: Date not supplied · evaluations.json · v2_Semi_Private Reported benchmark cost: $0.29 per task. Different from the token-workload estimate. Semi-private split only. Provider-adapter and custom-scaffold families are kept separate. Identical effort names do not imply identical compute budgets. Inspect source ↗Public leaderboard facts · ARC Prize | high / ARC Prize leaderboard baseline | ARC Prize ↗ |
|---|
| ARC-AGI-2 · semi-privateReasoning | 47.64%GPT-5.6 Luna (XHigh) ARC Prize official leaderboard · benchmark-publisher Run: Date not supplied · evaluations.json · v2_Semi_Private Reported benchmark cost: $0.54 per task. Different from the token-workload estimate. Semi-private split only. Provider-adapter and custom-scaffold families are kept separate. Identical effort names do not imply identical compute budgets. Inspect source ↗Public leaderboard facts · ARC Prize | xhigh / ARC Prize leaderboard baseline | ARC Prize ↗ |
|---|
| ARC-AGI-2 · semi-privateReasoning | 59.54%GPT-5.6 Luna (Max) ARC Prize official leaderboard · benchmark-publisher Run: Date not supplied · evaluations.json · v2_Semi_Private Reported benchmark cost: $0.67 per task. Different from the token-workload estimate. Semi-private split only. Provider-adapter and custom-scaffold families are kept separate. Identical effort names do not imply identical compute budgets. Inspect source ↗Public leaderboard facts · ARC Prize | max / ARC Prize leaderboard baseline | ARC Prize ↗ |
|---|