GPT-5.6 Sol: benchmark results

OpenAI's flagship GPT-5.6 tier for demanding reasoning, coding, and agentic tasks. Provider: OpenAI. Released 2026-07-09. Access: API.

Unified ELO 1761 ± 1, rank #14 of 1392 rated models, from 298 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
AI for Education Visual Maths91.14Accuracy (%)100
AI for Education Visual Maths - Number and Operations89.19Accuracy (%)100
AI for Education Visual Reasoning - odd one out88.3Accuracy (%)100
Agentic Commerce World85.6Overall (%)100
AgenticVBench38.4Average Success (%)100
BenchX - Pass Rate82.94Pass Rate (%)100
BoundaryBench (Unrestricted)83.9Success Rate (%)100
Creative Writing v32208Elo score (self-reported)100
DecBench57.2Exact Recovery (%)100
ExploitGym293Successful Intended Exploits (#)100
Graphwalks BFS 1M F183.4F1 (self-reported)100
Graphwalks BFS 256k F195.4F1 (self-reported)100

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