GPT-5.2 Codex (xHigh): benchmark results
GPT-5.2 Codex evaluated at the xhigh reasoning-effort setting. Provider: OpenAI. Released 2026-01-14. Access: API.
Unified ELO 1689 ± 1, rank #134 of 1761 rated models, from 24 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Context-Bench Filesystem | 93 | Rubric Score (%) | 100 |
| AA IFBench | 77.62 | Accuracy (%) | 96.4 |
| BinaryAudit | 90.67 | Avg Success Rate (%) | 96 |
| AA Long Context Reasoning | 82.33 | Accuracy (%) | 95.8 |
| AA-LCR | 79.33 | Accuracy (self-reported) | 95.4 |
| ALE-Bench | 1299.9 | Performance (Self-Refine x1) (self-reported) | 92 |
| AA GPQA Diamond | 89.9 | Accuracy (%) | 89.2 |
| AA Humanity's Last Exam | 35.73 | Accuracy (%) | 87.5 |
| AA TAU-2 Bench | 92.11 | Accuracy (%) | 87.5 |
| AA Omniscience - Health | 39.6 | Accuracy (%) | 86.7 |
| Artificial Analysis Intelligence Index | 33 | Intelligence Index | 85.2 |
| AA Omniscience - Humanities & Social Sciences | 39.94 | Accuracy (%) | 84.8 |
Interactive version: theaggregate.ai/model?slug=gpt-5-2-codex-xhigh · How It Works · Data refreshed daily, snapshot 2026-09-05.