GPT-5.5 Pro (xHigh): benchmark results
GPT-5.5 Pro evaluated at the xhigh reasoning-effort setting. Provider: OpenAI. Released 2026-04-23. Access: API.
Aggregate Rating 1929 ± 29, rank #22 of 2168 rated models, from 15 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| OTIS Mock AIME 2024-25 | 100 | Accuracy (%) | 98.2 |
| FrontierMath - Tiers 1-3 | 51 | Accuracy (%, 290 problems) | 98 |
| FrontierMath - Tier 4 | 39.6 | Accuracy (%, 48 problems) | 97.9 |
| AA CritPt | 30.57 | Accuracy (%) | 97.8 |
| CritPt | 30.6 | Accuracy (imported) | 96.8 |
| Epoch AI - GPQA Diamond | 93.92 | Accuracy (%) | 96 |
| FrontierMath - Tiers 1-3 (v2) | 87.72 | Accuracy (%, 285 private v2 problems) | 95.5 |
| Chess Puzzles (Epoch AI) | 62 | Accuracy (%) | 95.4 |
| Epoch AI - Critpt | 30.57 | Score | 94.8 |
| IMO-Bench | 88.1 | Advanced ProofBench Accuracy (%) | 90.9 |
| ARC-AGI-2 | 84.16 | Accuracy (%) | 87.6 |
| ARC-AGI-1 | 95 | Accuracy (%) | 87.3 |
Interactive version: theaggregate.ai/model?slug=gpt-5-5-pro-xhigh · How It Works · Data refreshed daily, snapshot 2026-10-20.