GPT-5.2 Codex (High): benchmark results
GPT-5.2 Codex evaluated at the high reasoning-effort setting. Provider: OpenAI. Released 2025-12-18. Access: API.
Aggregate Rating 1737 ± 24, rank #299 of 2284 rated models, from 31 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| SWE-AGI (Hard) - Test-Suite Pass Rate | 91.2 | Test-suite pass rate (%, 0-100): mean over the 8 hard-tier S | 100 |
| BinaryAudit | 88.41 | Avg Success Rate (%) | 88 |
| SWE-AGI (Easy) | 6 | Tasks passed (out of 6): the easy-tier SWE-AGI tasks whose f | 83.3 |
| SWE-AGI (Easy) - Test-Suite Pass Rate | 100 | Test-suite pass rate (%, 0-100): mean over the 6 easy-tier S | 83.3 |
| SlopCodeBench (Just Solve) - Isolated | 21.9 | Isolated solve rate (%): share of the 196 checkpoints whose | 82.4 |
| APEX-Agents | 42.2 | Mean Score (ReAct) (imported) | 79.5 |
| WeaveBench - Data Analysis and Visualization | 15.4 | PassRate (%) on the Data Analysis and Visualization domain t | 72.2 |
| SlopCodeBench (Just Solve) | 9.7 | Strict solve rate (%): share of the 196 checkpoints whose wo | 70.6 |
| SWE-AGI (Medium) | 7 | Tasks passed (out of 8): the medium-tier SWE-AGI tasks whose | 66.7 |
| SWE-AGI (Medium) - Test-Suite Pass Rate | 98.9 | Test-suite pass rate (%, 0-100): mean over the 8 medium-tier | 66.7 |
| WeaveBench - DevOps | 16.7 | PassRate (%) on the DevOps domain tasks of 114 long-horizon | 61.1 |
| Sonar LLM Leaderboard - Java - Pass Rate | 80.33 | Passing tests (%) | 60.2 |
Interactive version: theaggregate.ai/model?slug=gpt-5-2-codex-high · How It Works · Data refreshed daily, snapshot 2026-11-21.