Model
Claude 2
Anthropic · closed weights
Knowledge & Reasoning
Knowledge & Reasoning| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| ARC-Challenge | 91.0 | accuracy | N/A | Independent | medium | www-files.anthropic.com |
| GPQA Diamond | 34.7 | accuracy | N/A | Independent | high | epoch.ai |
| MMLU | 78.5 | exact_match | N/A | Self-reported | medium | www-cdn.anthropic.com |
| Trivia QA | 87.5 | exact_match | N/A | Self-reported | medium | www-cdn.anthropic.com |
| Trivia QA | 87.5 | exact_match | N/A | Independent | medium | www-files.anthropic.com |
Long Context
Long Context| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| Ada-LEval | 65.0 | 1k | N/A | Independent | medium | paperswithcode.com |
| Ada-LEval (TSort) | 5.0 | 2k | N/A | Independent | medium | paperswithcode.com |
| QuALITY | 83.2 | accuracy | N/A | Independent | medium | www-files.anthropic.com |
Reproduced by the community
Loading community runs…