GPT-5.6 Sol (Max): benchmark results
GPT-5.6 Sol evaluated at the max reasoning-effort setting. Provider: OpenAI. Released 2026-07-09. Access: API.
Unified ELO 1772 ± 1, rank #17 of 1761 rated models, from 124 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA CritPt | 32.29 | Accuracy (%) | 100 |
| AA Terminal-Bench Hard | 65.91 | Accuracy (%) | 100 |
| E-Commerce Bench | 1431 | Final Assets (¥k, mean of 5 episodes) | 100 |
| Epoch AI - Critpt | 32.3 | Score | 100 |
| GDP.pdf | 30.7 | Strict Pass Rate (%) | 100 |
| HWE-Bench (Codex CLI) | 79.9 | Resolved (%) | 100 |
| MathArena - ARXIV June | 86.73 | Accuracy (%) | 100 |
| Riemann-bench | 74.4 | Score (%) | 100 |
| Vals AI ReverseEngBench | 30.53 | Fully Solved (%) | 100 |
| ZeroBench | 30 | Score (%) | 100 |
| Vals AI GPQA | 95.2 | Accuracy (%) | 99.3 |
| ARC-AGI-2 | 92.5 | Accuracy (%) | 99.1 |
Interactive version: theaggregate.ai/model?slug=gpt-5-6-sol-max · How It Works · Data refreshed daily, snapshot 2026-09-05.