Skip to content
English

Switch theme

Google

Gemma 4 26B A4B benchmark results

5 results on 5 benchmarks from 2 sources.

Open weights Released: Apr 2, 2026 Updated Oct 22, 2026 API prices & specs →

Also listed as: gemma-4-26b-a4b · gemma-4-26b-a4b-it_minimal

All benchmark results

Benchmarks Score Rank Setting Source type Date
LMArena Text 1438 100 Overall, style control on; 6092 votes; 95% CI 1430–1445“gemma-4-26b-a4b” Official leaderboard Oct 8, 2026
LMArena WebDev 1359 106 Overall; 1502 votes; 95% CI 1342–1376“gemma-4-26b-a4b” Official leaderboard Oct 8, 2026
LMArena Vision 1242 59 Overall, style control on; 23954 votes; 95% CI 1235–1248“gemma-4-26b-a4b” Official leaderboard Oct 2, 2026
GPQA Diamond 73.2% 148 Epoch AI run, accuracy Independent run Aug 6, 2026
AIME (OTIS Mock AIME 2024–2025) 82.2% 105 Epoch AI run, OTIS Mock AIME 2024–2025 Independent run Aug 28, 2026

Related on this site

← AI Model Benchmarks

FAQ

Where do these Gemma 4 26B A4B scores come from?

From Epoch AI Benchmarking Hub and LMArena leaderboard dataset. Each row links to the original leaderboard, dataset or report, and vendor-reported numbers are labelled.

Data updated: Benchmarks(UTC+8)