Skip to content
English

Switch theme

MiniMax

MiniMax-M3 benchmark results

6 results on 6 benchmarks from 2 sources.

Open weights Released: Jun 1, 2026 Updated Oct 22, 2026 API prices & specs →

Also listed as: minimax-m3 · MiniMax-M3_none · MiniMax M3 (enabled)

All benchmark results

Benchmarks Score Rank Setting Source type Date
LMArena Text 1441 96 Overall, style control on; 61220 votes; 95% CI 1437–1444“minimax-m3” Official leaderboard Oct 8, 2026
LMArena WebDev 1482 62 Overall; 18288 votes; 95% CI 1476–1487“minimax-m3” Official leaderboard Oct 8, 2026
LMArena Vision 1237 63 Overall, style control on; 18308 votes; 95% CI 1230–1243“minimax-m3” Official leaderboard Oct 2, 2026
GPQA Diamond 81.3% 110 Epoch AI run, accuracy Independent run Aug 10, 2026
AIME (OTIS Mock AIME 2024–2025) 26.7% 197 Epoch AI run, OTIS Mock AIME 2024–2025 Independent run Aug 10, 2026
OSWorld 2.0 4.6% 12 Binary accuracy; 500 steps; reasoning: enabled Official leaderboard via Epoch AI Jun 1, 2026

Related on this site

← AI Model Benchmarks

FAQ

Where do these MiniMax-M3 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)