OpenAI·released 2024-01-251 source
GPT-4 Turbo (Nov 2023) benchmark scores: 6 benchmarks tracked. 33% of its scores are independently reproduced — the rest are self-reported or unverified.
Leads on 0 of 6 benchmarks·best result 72.8 on MMLU (unverified)·2 of 6 independently reproduced
| Benchmark | Score | Evidence status | Measured |
|---|---|---|---|
| MMLU | 72.8accuracy (%) | unverified· optimizedT1 | 2023-11-06Stanford CRFM Leaderboard |
| MATH level 5 | 40.02accuracy (%) | reproduced· optimizedT1 | 2024-01-25Epoch AI |
| DTBench | 36accuracy (%) | unverifiedT1 | 2023-11-06https://conceptualreasoning.ai/dtbench |
| METR Time Horizons | 35.17accuracy (%) | unverifiedT1 | 2024-01-25METR - Measuring AI Ability to Complete Long Tasks |
| GPQA diamond | 23.15accuracy (%) | reproduced· optimizedT1 | 2024-01-25Epoch AI |
| LMCA | 11.51accuracy (%) | unverifiedT1 | 2023-11-06https://conceptualreasoning.ai/lmca |
Claims drawn from cited facts, not live model generation.
This model was developed by OpenAI and released in 2024.
2 cited facts
This model is scored on 6 tracked benchmarks, and it currently holds no top score on any of them. Its record can be trusted: the scores have been independently reproduced, meaning outside evaluation backs them up.
3 cited facts
On average this model trails the state-of-the-art leader by about 51.4 points across its benchmarks, measured as a raw score gap under the disclosed harness rather than any statement about capability. That wide a margin reads as well behind the front of the pack, consistent with holding the top score on none of its benchmarks — no category leadership yet.
3 cited facts
1 facts cross-checked across data sources: 1 single-source.
Source facts, citations, and refresh stamp for this record.
Sources: epoch_benchmarks
GPT-4 Turbo (Nov 2023) is an AI model developed by OpenAI, released 2024-01-25. Its benchmark record below tags every score as independently reproduced, self-reported, or unverified.
GPT-4 Turbo (Nov 2023) has recorded scores on 6 benchmarks, each shown with its evidence status.
GPT-4 Turbo (Nov 2023) has recorded scores on 6 benchmarks — GPQA diamond, MATH level 5, DTBench, MMLU, LMCA, METR Time Horizons. The full table above shows each score with its evidence status.
2 of 6 recorded scores (33%) are independently reproduced rather than self-reported by the lab.
GPT-4 Turbo (Nov 2023) has 6 tracked claims: 2 independently reproduced, 4 unverified.