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 1746 ± 1, rank #36 of 1761 rated models, from 58 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Computer Anthology Terminal Tasks (Codex CLI) | 58 | pass@1 (%) | 100 |
| LLM Chess (Saplin) | 1548.5 | ELO | 99.4 |
| PM-LLM-Benchmark | 39.8 | Score | 99.4 |
| AA Terminal-Bench Hard | 62.12 | Accuracy (%) | 99.1 |
| EnigmaEval | 37.12 | Score (self-reported) | 98 |
| AA Omniscience - Science, Engineering & Mathematics | 54.3 | Accuracy (%) | 97.8 |
| AA Omniscience - Health | 51.9 | Accuracy (%) | 97.5 |
| AA Omniscience - Humanities & Social Sciences | 57.3 | Accuracy (%) | 97.5 |
| AA-Omniscience Accuracy | 58.35 | Accuracy (%) | 96.9 |
| AA Omniscience - Business | 48.6 | Accuracy (%) | 96.5 |
| AA Omniscience - Software Engineering (SWE) | 83.8 | Accuracy (%) | 96.3 |
| Artificial Analysis Intelligence Index | 48.3 | Intelligence Index | 96.3 |
Interactive version: theaggregate.ai/model?slug=gpt-5-6-sol-high · How It Works · Data refreshed daily, snapshot 2026-09-05.