Anthropic·released 2023-08-091 source
Claude Instant benchmark scores: 5 benchmarks tracked. 0% of its scores are independently reproduced — the rest are self-reported or unverified.
Leads on 0 of 5 benchmarks·best result 86.7 on GSM8K (unverified)·0 of 5 independently reproduced
| Benchmark | Score | Evidence status | Measured |
|---|---|---|---|
| GSM8K | 86.7accuracy (%) | unverified· optimizedT1 | 2023-08-09Releasing Claude Instant 1.2 |
| ARC AI2 | 81.73accuracy (%) | unverified· optimizedT1 | 2023-08-09Releasing Claude Instant 1.2 |
| TriviaQA | 78.9accuracy (%) | self-reported· optimizedT1 | 2023-08-09Model Card and Evaluations for Claude Models |
| MMLU | 64.53accuracy (%) | self-reported· optimizedT1 | 2023-08-09Model Card and Evaluations for Claude Models |
| DTBench | 9.63accuracy (%) | unverifiedT1 | 2023-08-09https://conceptualreasoning.ai/dtbench |
Claims drawn from cited facts, not live model generation.
This model originated from Anthropic. Its vintage is 2023, the year it was released.
2 cited facts
This model is scored on 5 tracked benchmarks, but it holds no current top score on any of them. Its numbers are vendor-claimed and have not yet been independently confirmed, so they should be read as claims rather than verified results.
3 cited facts
On average this model trails the best reported score on its benchmarks by 26.66 points, a wide gap under the disclosed harness that reads as well behind the leaders rather than merely short of the front of the pack. Consistently, it holds the top score on none of its benchmarks (sota leader count of 0), so there is no category in which it can claim genuine leadership yet.
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 Instant is an AI model developed by Anthropic, released 2023-08-09. Its benchmark record below tags every score as independently reproduced, self-reported, or unverified.
Claude Instant has recorded scores on 5 benchmarks, each shown with its evidence status.
Claude Instant has recorded scores on 5 benchmarks — TriviaQA, DTBench, MMLU, ARC AI2, GSM8K. The full table above shows each score with its evidence status.
0 of 5 recorded scores (0%) are independently reproduced rather than self-reported by the lab.
Claude Instant has 5 tracked claims: 2 self-reported, 3 unverified.