Anthropic·released 2023-11-211 source
Claude 2.1 benchmark scores: 5 benchmarks tracked. 40% of its scores are independently reproduced — the rest are self-reported or unverified.
Leads on 0 of 5 benchmarks·best result 64.67 on MMLU (unverified)·2 of 5 independently reproduced
| Benchmark | Score | Evidence status | Measured |
|---|---|---|---|
| MMLU | 64.67accuracy (%) | unverified· optimizedT1 | 2023-11-21Stanford CRFM Leaderboard |
| DTBench | 18.25accuracy (%) | unverifiedT1 | 2023-11-21https://conceptualreasoning.ai/dtbench |
| GPQA diamond | 10.61accuracy (%) | reproduced· optimizedT1 | 2023-11-21Epoch AI |
| WeirdML | 7.06accuracy (%) | unverifiedT1 | 2023-11-21https://htihle.github.io/weirdml.html |
| OTIS Mock AIME 2024-2025 | 1.85accuracy (%) | reproduced· optimizedT1 | 2023-11-21Epoch AI |
Claims drawn from cited facts, not live model generation.
This model was developed by Anthropic. Its vintage is 2023, which places it among the earlier waves of large-scale generative models rather than the most recent releases.
2 cited facts
It is scored on five tracked benchmarks and currently holds no top score among them. Its record is independently reproduced, so outside evaluation backs the scores up.
3 cited facts
On average this model trails the best reported score on its benchmarks by 73.26 points, a gap under a disclosed harness rather than a capability claim; a margin of that size reads plainly as well behind the leaders, not a near-frontier result. It holds the top score on 0 benchmarks, meaning there is no category in which it currently leads.
2 cited facts
1 facts cross-checked across data sources: 1 single-source.
Source facts, citations, and refresh stamp for this record.
Sources: epoch_benchmarks
Claude 2.1 is an AI model developed by Anthropic, released 2023-11-21. Its benchmark record below tags every score as independently reproduced, self-reported, or unverified.
Claude 2.1 has recorded scores on 5 benchmarks, each shown with its evidence status.
Claude 2.1 has recorded scores on 5 benchmarks — GPQA diamond, OTIS Mock AIME 2024-2025, DTBench, WeirdML, MMLU. The full table above shows each score with its evidence status.
2 of 5 recorded scores (40%) are independently reproduced rather than self-reported by the lab.
Claude 2.1 has 5 tracked claims: 2 independently reproduced, 3 unverified.