LIVE INTELLIGENCE · part of the Xentir AI Index

Gemini 3.1 Pro Preview vs GPT-5.6 Luna

Gemini 3.1 Pro Preview · Google DeepMind, released 2026-02-19
GPT-5.6 Luna · 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 — Gemini 3.1 Pro Preview leads on 3, GPT-5.6 Luna leads on 2.

Benchmark	Gemini 3.1 Pro Preview	GPT-5.6 Luna	Leads
Epoch Capabilities Index (ECI)	154.9	155.3	GPT-5.6 Luna
SWE-bench Verified	0.756 (customtools)	Not measured	Not measured on both
GPQA Diamond	0.941	0.916 (max)	Gemini 3.1 Pro Preview
MATH Level 5	Not measured	Not measured	Not measured on both
OTIS Mock AIME 2024-2025	0.956	0.983 (max)	GPT-5.6 Luna
FrontierMath	0.369	Not measured	Not measured on both
FrontierMath Tier 4	0.167	Not measured	Not measured on both
SimpleQA Verified	0.773	0.417 (max)	Gemini 3.1 Pro Preview
Chess Puzzles	0.550	0.400 (max)	Gemini 3.1 Pro Preview

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

Gemini 3.1 Pro Preview → · GPT-5.6 Luna → · the full AI Model Rankings table