GPT-5.5 (High) — benchmark results
GPT-5.5 evaluated at the high reasoning-effort setting. Provider: OpenAI. Released 2026-04-23. Access: API.
Unified ELO 2011 ± 26, rank #20 of 1776 rated models, from 96 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA Omniscience - Software Engineering (SWE) - C | 92 | Accuracy (%) | 100 |
| Buyout Game (Lechmazur) | 1975.4 | Bradley-Terry Rating | 100 |
| PACT (Lechmazur) | 1607 | CMS Points | 100 |
| Shader Benchmark | 242.2 | Avg judge score (0-500, render fails count 0) | 100 |
| SlopCodeBench | 28.06 | Isolated Solved (%) | 100 |
| UGI - Natural Intelligence | 79.27 | NatInt Score | 100 |
| AA Omniscience - Software Engineering (SWE) - HTML | 90 | Accuracy (%) | 99.7 |
| AA Omniscience - Science, Engineering & Mathematics | 52.3 | Accuracy (%) | 99.6 |
| AA Omniscience - Software Engineering (SWE) - R | 74 | Accuracy (%) | 99.6 |
| AA GPQA Diamond | 93.23 | Accuracy (%) | 99.3 |
| AA Omniscience - Software Engineering (SWE) | 83.9 | Accuracy (%) | 99.3 |
| LLM Chess (Saplin) | 1528.4 | ELO | 99.3 |
Interactive version: theaggregate.ai/model?slug=gpt-5-5-high · How the rankings work · Data refreshed daily, snapshot 2026-07-22.