Model
Claude Haiku 5.5
Anthropic · closed weights
Knowledge & Reasoning
Knowledge & Reasoning| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| CritPt | 22.6 | accuracy | N/A | Independent | low | epoch.ai |
| GPQA Diamond | 89.6 | accuracy | N/A | Independent | high | epoch.ai |
| HLE | 30.1 | accuracy | N/A | Independent | low | epoch.ai |
| SimpleQA Verified | 23.8 | accuracy | N/A | Independent | high | epoch.ai |
Coding
Coding| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| SciCode | 55.0 | score | N/A | Independent | medium | artificialanalysis.ai |
Agentic / Tool Use
Agentic / Tool Use| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| ToolBottleneckBench | 4.5 | success_rate | toolbottleneckbench | Independent | medium | arxiv.org |
Reproduced by the community
Loading community runs…