OpenAI·released 2024-08-061 source
GPT-4o (Aug 2024) benchmark scores: 10 benchmarks tracked. 30% of its scores are independently reproduced — the rest are self-reported or unverified.
Leads on 0 of 10 benchmarks·best result 79.07 on MMLU (unverified)·3 of 10 independently reproduced
| Benchmark | Score | Evidence status | Measured |
|---|---|---|---|
| MMLU | 79.07accuracy (%) | unverified· optimizedT1 | 2024-08-06Stanford CRFM Leaderboard |
| MATH level 5 | 53.28accuracy (%) | reproduced· optimizedT1 | 2024-08-06Epoch AI |
| GPQA diamond | 32.28accuracy (%) | reproduced· optimizedT1 | 2024-08-06Epoch AI |
| CadEval | 26accuracy (%) | unverifiedT1 | 2024-08-06CadEval Dashboard |
| SimpleQA Verified | 26accuracy (%) | unverifiedT2 | 2024-08-06 |
| Aider polyglot | 23.1accuracy (%) | unverified· optimizedT1 | 2024-08-06https://aider.chat/docs/leaderboards/ |
| OTIS Mock AIME 2024-2025 | 6.3accuracy (%) | reproduced· optimizedT1 | 2024-08-06Epoch AI |
| SimpleBench | 1.36accuracy (%) | unverifiedT1 | 2024-08-06SimpleBench Leaderboard |
| Chess Puzzles | 1.09accuracy (%) | unverifiedT2 | 2024-08-06 |
| FrontierMath-Tiers-1-3-v2-Private | 0.35accuracy (%) | unverifiedT2 | 2024-08-06 |
Claims drawn from cited facts, not live model generation.
This model was developed by OpenAI and released in 2024.
2 cited facts
This model has scores on 10 tracked benchmarks and currently leads 0 of them. The record’s evidence status is independently reproduced.
3 cited facts
Its mean gap to the best recorded score across its tracked benchmarks is 61.12 points.
1 cited fact
1 facts cross-checked across data sources: 1 single-source.
Source facts, citations, and refresh stamp for this record.
Sources: epoch_benchmarks
GPT-4o (Aug 2024) is an AI model developed by OpenAI, released 2024-08-06. Its benchmark record below tags every score as independently reproduced, self-reported, or unverified.
GPT-4o (Aug 2024) has recorded scores on 10 benchmarks, each shown with its evidence status.
GPT-4o (Aug 2024) has recorded scores on 10 benchmarks — GPQA diamond, MATH level 5, OTIS Mock AIME 2024-2025, CadEval, MMLU, SimpleQA Verified, and 4 more. The full table above shows each score with its evidence status.
3 of 10 recorded scores (30%) are independently reproduced rather than self-reported by the lab.
GPT-4o (Aug 2024) has 10 tracked claims: 3 independently reproduced, 7 unverified.