Skip to content
English

Switch theme

Google

Gemini 2.5 Pro (Mar 2025) benchmark results

4 results on 4 benchmarks from 2 sources.

Closed Released: Mar 25, 2025 Updated Oct 22, 2026

Also listed as: gemini-2.5-pro-exp-03-25 · Gemini 2.5 Pro Exp (Mar 2025) · gemini-2.5-pro-preview-03-25 · Gemini 2.5 Pro Preview (Mar 2025) · Gemini 2.5 Pro Experimental (March 2025) · Gemini-2.5-Pro-Exp-03-25

All benchmark results

Benchmarks Score Rank Setting Source type Date
GPQA Diamond 83.8% 92 Epoch AI run, accuracy; effort: Mar 2025 Independent run Mar 31, 2025
MMLU-Pro 84.5% 37 Overall accuracy; data source: TIGER-Lab“Gemini-2.5-Pro-Exp-03-25” Official leaderboard Mar 11, 2026
MATH Level 5 95.6% 13 Epoch AI run, accuracy; effort: Mar 2025 Independent run May 7, 2025
Humanity's Last Exam 18.2% 25 Compiled by Epoch AI; effort: Mar 2025 Third-party compilation via Epoch AI Mar 25, 2025

Related on this site

← AI Model Benchmarks

FAQ

Where do these Gemini 2.5 Pro (Mar 2025) scores come from?

From Epoch AI Benchmarking Hub and MMLU-Pro leaderboard (TIGER-Lab). Each row links to the original leaderboard, dataset or report, and vendor-reported numbers are labelled.

Data updated: Benchmarks(UTC+8)