Model
Claude Opus 4.1 (2025-08-05)
Anthropic · closed weights
Knowledge & Reasoning
Knowledge & Reasoning| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| EnigmaEval | 7.2 | accuracy | N/A | Independent | medium | labs.scale.com |
| GDPval | 43.6 | win_rate | N/A | Independent | low | epoch.ai |
| GPQA Diamond | 73.2 | accuracy | N/A | Independent | high | epoch.ai |
| HLE | 11.5 | accuracy | N/A | Independent | low | epoch.ai |
Coding
Coding| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| SWE-bench Verified | 73.3 | resolved_rate | N/A | Independent | high | epoch.ai |
Agentic / Tool Use
Agentic / Tool Use| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| DeepResearch Bench | 48.3 | average_score | N/A | Independent | medium | drb.futuresearch.ai |
| Terminal-Bench | 38.0 | accuracy | Terminus 2 | Independent | medium | tbench.ai |
| Terminal-Bench | 36.9 | accuracy | OpenHands | Independent | medium | tbench.ai |
| Terminal-Bench | 35.1 | accuracy | Mini-SWE-Agent | Independent | medium | tbench.ai |
| Terminal-Bench | 34.8 | accuracy | Claude Code | Independent | medium | tbench.ai |
Safety & Alignment
Safety & Alignment| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| Cybench | 42.0 | unguided_%_solved | N/A | Independent | medium | cybench.github.io |
Reproduced by the community
Loading community runs…