GPT-5.6 Sol (High) — benchmark results
GPT-5.6 Sol evaluated at the high reasoning-effort setting. Provider: OpenAI. Released 2026-07-09. Access: API.
Unified ELO 2041 ± 33, rank #15 of 1776 rated models, from 48 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA Omniscience - Health | 50.7 | Accuracy (%) | 100 |
| AA Omniscience - Software Engineering (SWE) - PHP | 94 | Accuracy (%) | 99.8 |
| AA Omniscience - Software Engineering (SWE) - TypeScript | 91.11 | Accuracy (%) | 99.4 |
| PM-LLM-Benchmark | 39.8 | Score | 99.4 |
| AA Omniscience - Humanities & Social Sciences | 57.4 | Accuracy (%) | 99.3 |
| AA Omniscience - Science, Engineering & Mathematics | 52.2 | Accuracy (%) | 99.3 |
| AA SciCode | 56.94 | Accuracy (%) | 99.3 |
| AA-Omniscience Accuracy | 57.32 | Accuracy (%) | 99.3 |
| Artificial Analysis Intelligence Index | 55.87 | Intelligence Index | 99.3 |
| WeirdML | 88.76 | Average Score | 99.3 |
| AA Omniscience - Software Engineering (SWE) - Go | 84 | Accuracy (%) | 99.2 |
| AA Omniscience - Software Engineering (SWE) - Kotlin | 86 | Accuracy (%) | 99.2 |
Interactive version: theaggregate.ai/model?slug=gpt-5-6-sol-high · How the rankings work · Data refreshed daily, snapshot 2026-07-22.