GPT-5.5 (Medium) — benchmark results
GPT-5.5 evaluated at the medium reasoning-effort setting. Provider: OpenAI. Released 2026-04-23. Access: API.
Unified ELO 1997 ± 34, rank #26 of 1776 rated models, from 60 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| LLM Chess (Saplin) | 1532.2 | ELO | 100 |
| UGI - Natural Intelligence | 77.12 | NatInt Score | 99.8 |
| AA Omniscience - Software Engineering (SWE) - HTML | 90 | Accuracy (%) | 99.7 |
| AA Omniscience - Software Engineering (SWE) - R | 74 | Accuracy (%) | 99.6 |
| AA Omniscience - Software Engineering (SWE) - Python | 89 | Accuracy (%) | 99.3 |
| AA Omniscience - Software Engineering (SWE) - Rust | 86 | Accuracy (%) | 99.2 |
| AA Omniscience - Software Engineering (SWE) - C | 88 | Accuracy (%) | 99.1 |
| AA Omniscience - Software Engineering (SWE) - PHP | 92 | Accuracy (%) | 99.1 |
| AA Omniscience - Software Engineering (SWE) - JavaScript | 88.18 | Accuracy (%) | 99 |
| AA Omniscience - Health | 48.8 | Accuracy (%) | 98.9 |
| AA Omniscience - Software Engineering (SWE) - Dart | 76 | Accuracy (%) | 98.9 |
| AA Omniscience - Software Engineering (SWE) - Java | 69 | Accuracy (%) | 98.8 |
Interactive version: theaggregate.ai/model?slug=gpt-5-5-medium · How the rankings work · Data refreshed daily, snapshot 2026-07-22.