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

BenchmarkScoreMetricPercentile
PrinzBench91Score (x/99)100
Conceptual Reasoning Index69.97Chance-Corrected Score (0-100)98.5
MineBench2108Elo Rating98.4
OpenRouter GPQA Diamond93.8Accuracy (%)98
Conceptual Reasoning Index - Decision Theory (DTBench)93.33Chance-Corrected Score (0-100)96.9
AI Chess Leaderboard (Reasoning)1617Elo96.3
Conceptual Reasoning Index - Consistency (ACCoRD)78.86Chance-Corrected Score (0-100)94
LM Market Cap LMC Score89LMC Score (0-100)91.7
Arabic Broad Leaderboard8.97Average Score (0-10)89.4
RadLE 2.0 (Radiology)665RadLE Score86.7
OpenRouter Tau2-Bench Airline76.7Accuracy (%)86.1

Interactive version: theaggregate.ai/model?slug=gpt-5-6-pro-sol · How It Works · Data refreshed daily, snapshot 2026-09-05.