Cybersecurity vulnerability remediation on CVE-Bench 1.0
90Pass@1 RateGPT-5.3-Codex system card
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| GPT-5.3-Codex system cardTime=2026.022026.05 | 90 | — |
Loading the SOTA2 catalog…
| Method | Links | ||
|---|---|---|---|
| GPT-5.3-Codex system cardTime=2026.022026.05 | 90 | — |