LIVE INTELLIGENCE · part of the Xentir AI Index

GPT-5.5 Pro vs GPT-5.6 Sol

GPT-5.5 Pro · OpenAI, released 2026-04-23
GPT-5.6 Sol · OpenAI, released 2026-07-09

“Epoch AI, 'AI Benchmarking Hub'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks' [online resource].” · epoch.ai/benchmarks · Licensed CC BY 4.0 · data last verified 2026-07-26 · Methodology · Data Sources

Head-to-head

Measured on 5 of 9 tracked benchmarks for both models — GPT-5.5 Pro leads on 1, GPT-5.6 Sol leads on 2, tied on 2.

Benchmark	GPT-5.5 Pro	GPT-5.6 Sol	Leads
Epoch Capabilities Index (ECI)	160.9	161.7	GPT-5.6 Sol
SWE-bench Verified	Not measured	Not measured	Not measured on both
GPQA Diamond	0.939 (xhigh-pre-release)	0.935 (max)	GPT-5.5 Pro
MATH Level 5	Not measured	Not measured	Not measured on both
OTIS Mock AIME 2024-2025	1.000 (xhigh-pre-release)	1.000 (max)	Tied
FrontierMath	0.524 (high-pre-release)	Not measured	Not measured on both
FrontierMath Tier 4	0.396	Not measured	Not measured on both
SimpleQA Verified	0.645 (xhigh-pre-release)	0.716 (max)	GPT-5.6 Sol
Chess Puzzles	0.640 (xhigh-pre-release)	0.640 (promax)	Tied

Benchmark results measure specific tasks and should not be treated as a universal measure of model quality. A model with no row here for a benchmark has not been measured on it — that is left blank, never estimated.

Full profiles

GPT-5.5 Pro → · GPT-5.6 Sol → · the full AI Model Rankings table