LIVE INTELLIGENCE · part of the Xentir AI Index

Gemini 3.1 Pro Preview vs GPT-5.2 Pro

Gemini 3.1 Pro Preview · Google DeepMind, released 2026-02-19
GPT-5.2 Pro · OpenAI, released 2025-12-11

“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 2 of 9 tracked benchmarks for both models — Gemini 3.1 Pro Preview leads on 1, GPT-5.2 Pro leads on 1.

Benchmark	Gemini 3.1 Pro Preview	GPT-5.2 Pro	Leads
Epoch Capabilities Index (ECI)	154.9	154.7	Gemini 3.1 Pro Preview
SWE-bench Verified	0.756 (customtools)	Not measured	Not measured on both
GPQA Diamond	0.941	Not measured	Not measured on both
MATH Level 5	Not measured	Not measured	Not measured on both
OTIS Mock AIME 2024-2025	0.956	Not measured	Not measured on both
FrontierMath	0.369	Not measured	Not measured on both
FrontierMath Tier 4	0.167	0.313 (webapp)	GPT-5.2 Pro
SimpleQA Verified	0.773	Not measured	Not measured on both
Chess Puzzles	0.550	Not measured	Not measured on both

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-5.2 Pro → · the full AI Model Rankings table