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 1978 ± 22, rank #32 of 1776 rated models, from 129 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
AI for Education Visual Reasoning - match (process)88.9Accuracy (%)100
AI for Education Visual Reasoning - odd one out88.3Accuracy (%)100
AI for Education Visual Reasoning - pattern completion (linear)92.3Accuracy (%)100
AgenticVBench38.4Average Success (%)100
Agents' Last Exam30.6Pass Rate (%)100
Benchmarks.bio - SpatialBench-Long38.89Pass Rate (%)100
Benchmarks.bio - scBench-Long38.1Pass Rate (%)100
DeepSWE72.7Pass@1 (%)100
ExploitGym293Successful Intended Exploits (#)100
LLM Stats (Artificial Analysis)59Score (%)100
LLM Stats (DeepSWE)72.7Score (%)100
LLM Stats (Graphwalks BFS >128k)90.7Score (%)100

Interactive version: theaggregate.ai/model?slug=gpt-5-6-sol · How the rankings work · Data refreshed daily, snapshot 2026-07-22.