OpenAI·released 2023-06-131 source
GPT-4 (Jun 2023) benchmark scores: 12 benchmarks tracked. 33% of its scores are independently reproduced — the rest are self-reported or unverified.
Leads on 0 of 12 benchmarks·best result 89.99 on GSM8K (unverified)·4 of 12 independently reproduced
| Benchmark | Score | Evidence status | Measured |
|---|---|---|---|
| GSM8K | 89.99accuracy (%) | unverified· optimizedT1 | 2023-06-13Baichuan 2: Open Large-scale Language Models |
| TriviaQA | 84.8accuracy (%) | unverified· optimizedT1 | 2023-06-13PapersWithCode |
| MMLU | 76.53accuracy (%) | unverified· optimizedT1 | 2023-06-13Stanford CRFM Leaderboard |
| BBH | 66.83accuracy (%) | unverified· optimizedT1 | 2023-06-13Baichuan 2: Open Large-scale Language Models |
| DTBench | 37.78accuracy (%) | unverifiedT1 | 2023-06-13https://conceptualreasoning.ai/dtbench |
| MATH level 5 | 22.97accuracy (%) | reproduced· optimizedT1 | 2023-06-13Epoch AI |
| LMCA | 20.07accuracy (%) | unverifiedT1 | 2023-06-13https://conceptualreasoning.ai/lmca |
| WeirdML | 12.36accuracy (%) | unverifiedT1 | 2023-06-13https://htihle.github.io/weirdml.html |
| GPQA diamond | 7.53accuracy (%) | reproduced· optimizedT1 | 2023-06-13Epoch AI |
| Mystery Game Puzzles | 3.06accuracy (%) | unverifiedT2 | 2023-06-13 |
| OTIS Mock AIME 2024-2025 | 1.01accuracy (%) | reproduced· optimizedT1 | 2023-06-13Epoch AI |
| Chess Puzzles | 0accuracy (%) | reproducedT1 | 2023-06-13Epoch AI |
Claims drawn from cited facts, not live model generation.
This model was developed by OpenAI and released in 2023.
2 cited facts
This model has scores on 12 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 53.9 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-4 (Jun 2023) is an AI model developed by OpenAI, released 2023-06-13. Its benchmark record below tags every score as independently reproduced, self-reported, or unverified.
GPT-4 (Jun 2023) has recorded scores on 12 benchmarks, each shown with its evidence status.
GPT-4 (Jun 2023) has recorded scores on 12 benchmarks — GPQA diamond, MATH level 5, OTIS Mock AIME 2024-2025, TriviaQA, DTBench, WeirdML, and 6 more. The full table above shows each score with its evidence status.
4 of 12 recorded scores (33%) are independently reproduced rather than self-reported by the lab.
GPT-4 (Jun 2023) has 12 tracked claims: 4 independently reproduced, 8 unverified.