Model
Claude 3 Haiku
Anthropic · closed weights
Knowledge & Reasoning
Knowledge & Reasoning| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| GPQA Diamond | 36.3 | accuracy | N/A | Independent | high | epoch.ai |
| MMLU | 75.2 | average_(%) | N/A | Independent | medium | anthropic.com |
| MMLU | 73.8 | exact_match | N/A | Independent | medium | crfm.stanford.edu |
| ScienceQA | 72.0 | score | N/A | Independent | medium | arxiv.org |
| WinoGrande | 74.2 | accuracy | N/A | Self-reported | medium | assets.anthropic.com |
| WinoGrande | 74.2 | accuracy | N/A | Independent | medium | anthropic.com |
Coding
Coding| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| MBPP | 80.4 | accuracy | N/A | Independent | medium | anthropic.com |
| PECC | 27.7 | pass@3 | N/A | Independent | medium | arxiv.org |
Safety & Alignment
Safety & AlignmentReproduced by the community
Loading community runs…