Model
GPT-5.3-codex
OpenAI · closed weights
Coding
Coding| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| SWE-bench Verified | 74.8 | resolved_rate | N/A | Independent | high | epoch.ai |
Agentic / Tool Use
Agentic / Tool Use| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| KlinikeBench | 3.6 | strict_pass@1 | N/A | Independent | medium | arxiv.org |
| Terminal-Bench | 78.4 | accuracy | SageAgent | Independent | medium | tbench.ai |
| Terminal-Bench | 77.3 | accuracy | Droid | Independent | medium | tbench.ai |
| Terminal-Bench | 75.8 | accuracy | CodeBrain-1.5 | Independent | medium | tbench.ai |
| Terminal-Bench | 75.7 | accuracy | Codelia | Independent | medium | tbench.ai |
| Terminal-Bench | 75.1 | accuracy | Simple Codex | Independent | medium | tbench.ai |
| Terminal-Bench | 74.6 | accuracy | Mux | Independent | medium | tbench.ai |
| Terminal-Bench | 71.5 | accuracy | spoox-o-m | Independent | medium | tbench.ai |
| Terminal-Bench | 70.3 | accuracy | CodeBrain-1 | Independent | low | epoch.ai |
| Terminal-Bench | 69.1 | accuracy | IndusAGI Coding Agent | Independent | medium | tbench.ai |
| Terminal-Bench | 64.7 | accuracy | Terminus 2 | Independent | medium | tbench.ai |
Reproduced by the community
Loading community runs…