Model
GPT-5.1 Codex mini
OpenAI · closed weights
Agentic / Tool Use
Agentic / Tool Use| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| Terminal-Bench | 61.6 | accuracy | hookele | Independent | medium | tbench.ai |
| Terminal-Bench | 43.1 | accuracy | Crux | Independent | medium | tbench.ai |
| Terminal-Bench | 43.1 | accuracy | Codex CLI | Independent | medium | tbench.ai |
Reproduced by the community
Loading community runs…