| GPQA diamondKnowledge | 88.89%gpt-5.4-2026-03-05_medium Epoch AI evaluation · epoch-run Run: 2026-07-15 · gpqa_diamond.csv Reported standard error: ±2.24 pp. This is not a 90% interval. Inspect source ↗CC BY 4.0 | medium / Epoch Inspect | Epoch AI run ↗ |
|---|
| GPQA diamondKnowledge | 74.75%gpt-5.4-2026-03-05_none Epoch AI evaluation · epoch-run Run: 2026-07-15 · gpqa_diamond.csv Reported standard error: ±3.10 pp. This is not a 90% interval. Inspect source ↗CC BY 4.0 | none / Epoch Inspect | Epoch AI run ↗ |
|---|
| GPQA diamondKnowledge | 89.90%gpt-5.4-2026-03-05_high Epoch AI evaluation · epoch-run Run: 2026-07-15 · gpqa_diamond.csv Reported standard error: ±2.15 pp. This is not a 90% interval. Inspect source ↗CC BY 4.0 | high / Epoch Inspect | Epoch AI run ↗ |
|---|
| GPQA diamondKnowledge | 84.85%gpt-5.4-2026-03-05_low Epoch AI evaluation · epoch-run Run: 2026-07-15 · gpqa_diamond.csv Reported standard error: ±2.55 pp. This is not a 90% interval. Inspect source ↗CC BY 4.0 | low / Epoch Inspect | Epoch AI run ↗ |
|---|
| GPQA diamondKnowledge | 93.30%gpt-5.4-2026-03-05_xhigh Epoch AI evaluation · epoch-run Run: 2026-03-06 · gpqa_diamond.csv Reported standard error: ±1.80 pp. This is not a 90% interval. Inspect source ↗CC BY 4.0 | xhigh / Epoch Inspect | Epoch AI run ↗ |
|---|
| FrontierMath-2025-02-28-PrivateReasoning | 47.60%gpt-5.4-2026-03-05_xhigh Epoch AI evaluation · epoch-run Run: 2026-03-06 · frontiermath.csv Reported standard error: ±2.90 pp. This is not a 90% interval. Inspect source ↗CC BY 4.0 | xhigh / Epoch Inspect | Epoch AI run ↗ |
|---|
| FrontierMath-Tier-4-2025-07-01-PrivateReasoning | 27.10%gpt-5.4-2026-03-05_xhigh Epoch AI evaluation · epoch-run Run: 2026-03-06 · frontiermath_tier_4.csv Reported standard error: ±6.40 pp. This is not a 90% interval. Inspect source ↗CC BY 4.0 | xhigh / Epoch Inspect | Epoch AI run ↗ |
|---|
| FrontierMath-Tiers-1-3-v2-PrivateReasoning | 78.60%gpt-5.4-2026-03-05_xhigh Epoch AI evaluation · epoch-run Run: 2026-06-11 · frontiermath_tiers_1_3_v2.csv Reported standard error: ±2.43 pp. This is not a 90% interval. Inspect source ↗CC BY 4.0 | xhigh / Epoch Inspect | Epoch AI run ↗ |
|---|
| FrontierMath-Tier-4-v2-PrivateReasoning | 49.00%gpt-5.4-2026-03-05_xhigh Epoch AI evaluation · epoch-run Run: 2026-06-11 · frontiermath_tier_4_v2.csv Reported standard error: ±8.00 pp. This is not a 90% interval. Inspect source ↗CC BY 4.0 | xhigh / Epoch Inspect | Epoch AI run ↗ |
|---|
| OTIS Mock AIME 2024-2025Reasoning | 95.56%gpt-5.4-2026-03-05_medium Epoch AI evaluation · epoch-run Run: 2026-07-15 · otis_mock_aime_2024_2025.csv Reported standard error: ±3.11 pp. This is not a 90% interval. Inspect source ↗CC BY 4.0 | medium / Epoch Inspect | Epoch AI run ↗ |
|---|
| OTIS Mock AIME 2024-2025Reasoning | 57.78%gpt-5.4-2026-03-05_none Epoch AI evaluation · epoch-run Run: 2026-07-15 · otis_mock_aime_2024_2025.csv Reported standard error: ±7.45 pp. This is not a 90% interval. Inspect source ↗CC BY 4.0 | none / Epoch Inspect | Epoch AI run ↗ |
|---|
| OTIS Mock AIME 2024-2025Reasoning | 97.78%gpt-5.4-2026-03-05_high Epoch AI evaluation · epoch-run Run: 2026-07-15 · otis_mock_aime_2024_2025.csv Reported standard error: ±2.22 pp. This is not a 90% interval. Inspect source ↗CC BY 4.0 | high / Epoch Inspect | Epoch AI run ↗ |
|---|
| OTIS Mock AIME 2024-2025Reasoning | 84.44%gpt-5.4-2026-03-05_low Epoch AI evaluation · epoch-run Run: 2026-07-15 · otis_mock_aime_2024_2025.csv Reported standard error: ±5.46 pp. This is not a 90% interval. Inspect source ↗CC BY 4.0 | low / Epoch Inspect | Epoch AI run ↗ |
|---|
| OTIS Mock AIME 2024-2025Reasoning | 95.30%gpt-5.4-2026-03-05_xhigh Epoch AI evaluation · epoch-run Run: 2026-03-06 · otis_mock_aime_2024_2025.csv Reported standard error: ±3.20 pp. This is not a 90% interval. Inspect source ↗CC BY 4.0 | xhigh / Epoch Inspect | Epoch AI run ↗ |
|---|
| SWE-Bench verifiedCoding | 76.86%gpt-5.4-2026-03-05_high Epoch AI evaluation · epoch-run Run: 2026-03-06 · swe_bench_verified.csv Reported standard error: ±1.92 pp. This is not a 90% interval. Inspect source ↗CC BY 4.0 | high / Epoch Inspect | Epoch AI run ↗ |
|---|
| SimpleQA VerifiedKnowledge | 45.10%gpt-5.4-2026-03-05_xhigh Epoch AI evaluation · epoch-run Run: 2026-08-27 · simpleqa_verified.csv Reported standard error: ±1.57 pp. This is not a 90% interval. Inspect source ↗CC BY 4.0 | xhigh / Epoch Inspect | Epoch AI run ↗ |
|---|
| Chess PuzzlesReasoning | 48.00%gpt-5.4-2026-03-05_xhigh Epoch AI evaluation · epoch-run Run: 2026-10-13 · chess_puzzles.csv Reported standard error: ±5.02 pp. This is not a 90% interval. Inspect source ↗CC BY 4.0 | xhigh / Epoch Inspect | Epoch AI run ↗ |
|---|
| Chess PuzzlesReasoning | 42.00%gpt-5.4-2026-03-05_high Epoch AI evaluation · epoch-run Run: 2026-10-13 · chess_puzzles.csv Reported standard error: ±4.96 pp. This is not a 90% interval. Inspect source ↗CC BY 4.0 | high / Epoch Inspect | Epoch AI run ↗ |
|---|
| Chess PuzzlesReasoning | 37.00%gpt-5.4-2026-03-05_medium Epoch AI evaluation · epoch-run Run: 2026-10-13 · chess_puzzles.csv Reported standard error: ±4.85 pp. This is not a 90% interval. Inspect source ↗CC BY 4.0 | medium / Epoch Inspect | Epoch AI run ↗ |
|---|
| Chess PuzzlesReasoning | 19.00%gpt-5.4-2026-03-05_low Epoch AI evaluation · epoch-run Run: 2026-10-13 · chess_puzzles.csv Reported standard error: ±3.94 pp. This is not a 90% interval. Inspect source ↗CC BY 4.0 | low / Epoch Inspect | Epoch AI run ↗ |
|---|
| Chess PuzzlesReasoning | 3.00%gpt-5.4-2026-03-05_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 ↗ |
|---|
| EBR-benchOther | 25.40%gpt-5.4-2026-03-05_xhigh Epoch AI evaluation · epoch-run Run: 2026-06-25 · ebr_bench.csv Inspect source ↗CC BY 4.0 | xhigh / Epoch Inspect | Epoch AI run ↗ |
|---|
| Mystery Game PuzzlesReasoning | 16.00%gpt-5.4-2026-03-05_none Epoch AI evaluation · epoch-run Run: 2026-08-30 · mystery_game_puzzles.csv Reported standard error: ±3.68 pp. This is not a 90% interval. Inspect source ↗CC BY 4.0 | none / Epoch Inspect | Epoch AI run ↗ |
|---|
| Mystery Game PuzzlesReasoning | 28.00%gpt-5.4-2026-03-05_medium Epoch AI evaluation · epoch-run Run: 2026-08-28 · mystery_game_puzzles.csv Reported standard error: ±4.51 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-5.4-2026-03-05_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 | 37.00%gpt-5.4-2026-03-05_xhigh Epoch AI evaluation · epoch-run Run: 2026-07-24 · mystery_game_puzzles.csv Reported standard error: ±4.85 pp. This is not a 90% interval. Inspect source ↗CC BY 4.0 | xhigh / Epoch Inspect | Epoch AI run ↗ |
|---|
| MirrorCodeCoding | 15.56%gpt-5.4-2026-03-05_high Epoch AI evaluation · epoch-run Run: 2026-08-10 · mirrorcode.csv Reported standard error: ±7.71 pp. This is not a 90% interval. Inspect source ↗CC BY 4.0 | high / Epoch Inspect | Epoch AI run ↗ |
|---|
| ARC-AGIReasoning | 93.67%gpt-5.4-2026-03-05_xhigh External result; evaluator not specified · external Run: Date not supplied · arc_agi_external.csv Inspect source ↗CC BY 4.0 | xhigh / Not reported | External · via Epoch ↗ |
|---|
| ARC-AGIReasoning | 93.67%gpt-5.4-2026-03-05_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 | 92.67%gpt-5.4-2026-03-05_high External result; evaluator not specified · external Run: Date not supplied · arc_agi_external.csv Inspect source ↗CC BY 4.0 | high / Not reported | External · via Epoch ↗ |
|---|
| ARC-AGIReasoning | 86.17%gpt-5.4-2026-03-05_medium External result; evaluator not specified · external Run: Date not supplied · arc_agi_external.csv Inspect source ↗CC BY 4.0 | medium / Not reported | External · via Epoch ↗ |
|---|
| ARC-AGIReasoning | 68.17%gpt-5.4-2026-03-05_low External result; evaluator not specified · external Run: Date not supplied · arc_agi_external.csv Inspect source ↗CC BY 4.0 | low / Not reported | External · via Epoch ↗ |
|---|
| DeepResearch BenchAgents | 35.10%gpt-5.4-2026-03-05_low https://evals.futuresearch.ai/#drb · external Run: Date not supplied · deepresearchbench_external.csv Inspect source ↗CC BY 4.0 | low / Not reported | External · via Epoch ↗ |
|---|
| GSO-BenchCoding | 31.37%gpt-5.4-2026-03-05_xhigh https://gso-bench.github.io/index.html · external Run: Date not supplied · gso_external.csv Inspect source ↗CC BY 4.0 | xhigh / Not reported | External · via Epoch ↗ |
|---|
| GSO-BenchCoding | 25.49%gpt-5.4-2026-03-05_high https://gso-bench.github.io/index.html · external Run: Date not supplied · gso_external.csv Inspect source ↗CC BY 4.0 | high / Not reported | External · via Epoch ↗ |
|---|
| Terminal BenchCoding | 81.80%gpt-5.4-2026-03-05_unknown https://www.tbench.ai/leaderboard/terminal-bench/2.0 · external Run: 2026-03-12 · terminalbench_external.csv Reported standard error: ±2.00 pp. This is not a 90% interval. Inspect source ↗CC BY 4.0 | unknown / ForgeCode | External · via Epoch ↗ |
|---|
| WeirdMLCoding | 77.70%gpt-5.4-2026-03-05_xhigh 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 | xhigh / Not reported | External · via Epoch ↗ |
|---|
| WeirdMLCoding | 57.44%gpt-5.4-2026-03-05_none WeirdML Leaderboard · external Run: Date not supplied · weirdml_external.csv Reported standard error: ±0.01 pp. This is not a 90% interval. Inspect source ↗CC BY 4.0 | none / Not reported | External · via Epoch ↗ |
|---|
| APEX-AgentsAgents | 52.40%gpt-5.4-2026-03-05_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 | 73.95%gpt-5.4-2026-03-05_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 | 73.95%gpt-5.4-2026-03-05_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 | 67.50%gpt-5.4-2026-03-05_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 | 55.42%gpt-5.4-2026-03-05_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 | 29.17%gpt-5.4-2026-03-05_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 ↗ |
|---|
| HLEKnowledge | 36.24%gpt-5.4-2026-03-05_xhigh External result; evaluator not specified · external Run: Date not supplied · hle_external.csv Reported standard error: ±1.88 pp. This is not a 90% interval. Inspect source ↗CC BY 4.0 | xhigh / Not reported | External · via Epoch ↗ |
|---|
| PostTrainBenchCoding | 19.00%gpt-5.4-2026-03-05_high External result; evaluator not specified · external Run: Date not supplied · posttrainbench_external.csv Inspect source ↗CC BY 4.0 | high / Not reported | External · via Epoch ↗ |
|---|
| GBAEvalOther | 45.15%gpt-5.4-2026-03-05_unknown https://gbaeval.com/model/gpt-5-4 · external Run: Date not supplied · gbaeval_external.csv Inspect source ↗CC BY 4.0 | unknown / Not reported | External · via Epoch ↗ |
|---|
| CritPtOther | 23.43%gpt-5.4-2026-03-05_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 ↗ |
|---|
| CL-benchOther | 27.90%gpt-5.4-2026-03-05_xhigh External result; evaluator not specified · external Run: Date not supplied · cl_bench_external.csv Inspect source ↗CC BY 4.0 | xhigh / Not reported | External · via Epoch ↗ |
|---|
| CL-bench LifeOther | 21.70%gpt-5.4-2026-03-05_xhigh External result; evaluator not specified · external Run: Date not supplied · cl_bench_life_external.csv Inspect source ↗CC BY 4.0 | xhigh / Not reported | External · via Epoch ↗ |
|---|
| CL-bench LifeOther | 19.30%gpt-5.4-2026-03-05_high External result; evaluator not specified · external Run: Date not supplied · cl_bench_life_external.csv Inspect source ↗CC BY 4.0 | high / Not reported | External · via Epoch ↗ |
|---|
| CL-bench LifeOther | 13.80%gpt-5.4-2026-03-05_unknown External result; evaluator not specified · external Run: Date not supplied · cl_bench_life_external.csv Inspect source ↗CC BY 4.0 | unknown / Not reported | External · via Epoch ↗ |
|---|
| METR Time HorizonsOther | 74.34%gpt-5.4-2026-03-05_xhigh https://metr.org/blog/2025-03-19-measuring-ai-ability-to-complete-long-tasks/ · external Run: Date not supplied · metr_time_horizons_external.csv Inspect source ↗CC BY 4.0 | xhigh / Not reported | External · via Epoch ↗ |
|---|
| DeepSWECoding | 51.77%gpt-5.4-2026-03-05_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 ↗ |
|---|
| ProofBenchReasoning | 56.00%gpt-5.4-2026-03-05_xhigh https://www.vals.ai/benchmarks/proof_bench · external Run: Date not supplied · proofbench_external.csv Reported standard error: ±4.96 pp. This is not a 90% interval. ProofBench v1.0-era value; model absent from the v1.1 board (vals.ai re-grade 2026-08-14, methodology changed) and not re-run. Not comparable to v1.1 rows. Annotated 2026-08-18. Inspect source ↗CC BY 4.0 | xhigh / Not reported | External · via Epoch ↗ |
|---|
| LMCAReasoning | 51.97%gpt-5.4-2026-03-05_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 ↗ |
|---|
| DTBenchReasoning | 94.40%gpt-5.4-2026-03-05_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 ↗ |
|---|
| Furniture AssemblyReasoning | 37.50%gpt-5.4-2026-03-05_xhigh Epoch AI evaluation · epoch-run Run: 2026-09-10 · furniture_assembly.csv Reported standard error: ±6.25 pp. This is not a 90% interval. Inspect source ↗CC BY 4.0 | xhigh / Epoch Inspect | Epoch AI run ↗ |
|---|
| EnigmaEvalOther | 15.96%gpt-5.4-2026-03-05_xhigh https://labs.scale.com/leaderboard/enigma_eval · external Run: Date not supplied · enigma_eval_external.csv Reported standard error: ±2.09 pp. This is not a 90% interval. Inspect source ↗CC BY 4.0 | xhigh / Not reported | External · via Epoch ↗ |
|---|
| ARC-AGI-2 · semi-privateReasoning | 29.17%GPT-5.4 (Low) ARC Prize official leaderboard · benchmark-publisher Run: Date not supplied · evaluations.json · v2_Semi_Private Reported benchmark cost: $0.27 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 | 55.42%GPT-5.4 (Medium) ARC Prize official leaderboard · benchmark-publisher Run: Date not supplied · evaluations.json · v2_Semi_Private Reported benchmark cost: $0.68 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 | 67.50%GPT-5.4 (High) ARC Prize official leaderboard · benchmark-publisher Run: Date not supplied · evaluations.json · v2_Semi_Private Reported benchmark cost: $1.02 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 | 73.95%GPT-5.4 (XHigh) ARC Prize official leaderboard · benchmark-publisher Run: Date not supplied · evaluations.json · v2_Semi_Private Reported benchmark cost: $1.52 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 ↗ |
|---|