GPT-5.6 Pro Sol: benchmark results
Provider: OpenAI. Released 2026-07-09. Access: API.
Unified ELO 1772 ± 1, rank #10 of 1392 rated models, from 11 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| PrinzBench | 91 | Score (x/99) | 100 |
| Conceptual Reasoning Index | 69.97 | Chance-Corrected Score (0-100) | 98.5 |
| MineBench | 2108 | Elo Rating | 98.4 |
| OpenRouter GPQA Diamond | 93.8 | Accuracy (%) | 98 |
| Conceptual Reasoning Index - Decision Theory (DTBench) | 93.33 | Chance-Corrected Score (0-100) | 96.9 |
| AI Chess Leaderboard (Reasoning) | 1617 | Elo | 96.3 |
| Conceptual Reasoning Index - Consistency (ACCoRD) | 78.86 | Chance-Corrected Score (0-100) | 94 |
| LM Market Cap LMC Score | 89 | LMC Score (0-100) | 91.7 |
| Arabic Broad Leaderboard | 8.97 | Average Score (0-10) | 89.4 |
| RadLE 2.0 (Radiology) | 665 | RadLE Score | 86.7 |
| OpenRouter Tau2-Bench Airline | 76.7 | Accuracy (%) | 86.1 |
Interactive version: theaggregate.ai/model?slug=gpt-5-6-pro-sol · How It Works · Data refreshed daily, snapshot 2026-09-05.