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 1736 ± 1, rank #45 of 1761 rated models, from 125 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Buyout Game (Lechmazur) | 1975.4 | Bradley-Terry Rating | 100 |
| FutureX | 49.19 | Overall Score (latest week, %) | 100 |
| OpenCompass Code - Comprehensive | 96.5 | Score (%) | 100 |
| OpenCompass LLM - Code | 96.5 | Score (%) | 100 |
| PACT (Lechmazur) | 1607 | PACT Bilateral Rating | 100 |
| Shader Benchmark | 242.2 | Avg judge score (0-500, render fails count 0) | 100 |
| SlopCodeBench | 28.06 | Isolated Solved (%) | 100 |
| SuperCLUE-LongContext - 1M Overall | 91.98 | Score | 100 |
| SuperCLUE-LongContext - 256K Overall | 98.24 | Score | 100 |
| UGI - Natural Intelligence | 79.27 | NatInt Score | 100 |
| Vals AI Terminal-Bench 2.0 | 73.2 | Accuracy (%) | 100 |
| AA Long Context Reasoning | 84.33 | Accuracy (%) | 99.2 |
Interactive version: theaggregate.ai/model?slug=gpt-5-5-high · How It Works · Data refreshed daily, snapshot 2026-09-05.