Anthropic·released 2024-02-291 source
Claude 3 Sonnet benchmark scores: 7 benchmarks tracked. 43% of its scores are independently reproduced — the rest are self-reported or unverified.
Leads on 0 of 7 benchmarks·best result 67.87 on MMLU (unverified)·3 of 7 independently reproduced
| Benchmark | Score | Evidence status | Measured |
|---|---|---|---|
| MMLU | 67.87accuracy (%) | unverified· optimizedT1 | 2024-02-29Stanford CRFM Leaderboard |
| Winogrande | 50.2accuracy (%) | unverified· optimizedT1 | 2024-02-29The Claude 3 Model Family: Opus, Sonnet, Haiku |
| DTBench | 22.67accuracy (%) | unverifiedT1 | 2024-02-29https://conceptualreasoning.ai/dtbench |
| GPQA diamond | 20.79accuracy (%) | reproduced· optimizedT1 | 2024-02-29Epoch AI |
| MATH level 5 | 18.17accuracy (%) | reproduced· optimizedT1 | 2024-02-29Epoch AI |
| WeirdML | 10.16accuracy (%) | unverifiedT1 | 2024-02-29https://htihle.github.io/weirdml.html |
| OTIS Mock AIME 2024-2025 | 2.4accuracy (%) | reproduced· optimizedT1 | 2024-02-29Epoch AI |
Claims drawn from cited facts, not live model generation.
This model was developed by Anthropic and released in 2024.
2 cited facts
It is scored on 7 tracked benchmarks. Among those, it holds no current top score. The record is independently reproduced, meaning outside evaluation backs the scores up.
3 cited facts
It trails the leader on average by 64.71 points under the disclosed harness. That wide gap reads as well behind the leaders.
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
Claude 3 Sonnet is an AI model developed by Anthropic, released 2024-02-29. Its benchmark record below tags every score as independently reproduced, self-reported, or unverified.
Claude 3 Sonnet has recorded scores on 7 benchmarks, each shown with its evidence status.
Claude 3 Sonnet has recorded scores on 7 benchmarks — Winogrande, GPQA diamond, MATH level 5, OTIS Mock AIME 2024-2025, DTBench, WeirdML, and 1 more. The full table above shows each score with its evidence status.
3 of 7 recorded scores (43%) are independently reproduced rather than self-reported by the lab.
Claude 3 Sonnet has 7 tracked claims: 3 independently reproduced, 4 unverified.