The Model Index
Up to four models

Mistral Large 4 vs MiniMax-M3

On the index (GPT-4 = 100), Mistral Large 4 scores 148 and MiniMax-M3 147. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.

Next to Mistral Large 4
Presets
Mistral Large 4
148132–165
WeightsOpen
ReleasedOct 2026
Price in / out$0.70 / $2.1
Context1.05M
Core tests taken3 of 9
MiniMax-M3
147131–164
WeightsOpen
ReleasedJun 2026
Price in / out$0.30 / $1.2
Context1.05M
Core tests taken4 of 9

Mistral Large 4 and MiniMax-M3 are too close to call (1 point apart, within the uncertainty), ahead on 1 of 2 shared core tests, at 2.0× the price.

Test by testthird-party results

Mistral Large 4MiniMax-M3
0%25%50%75%100%REASONING & KNOWLEDGEGPQA Diamond (Epoch AI)GPQA Diamond (Epoch AI)MATHSAIME-style maths (OTIS mock)AIME-style maths (OTIS mock)Chess puzzlesChess puzzlesSurface Evolver BenchSurface Evolver BenchAGENTSAPEX-AgentsAPEX-AgentsDTBenchDTBenchLMCALMCAMystery game puzzlesMystery game puzzles
Every result as a table
TestMistral Large 4MiniMax-M3
Reasoning & knowledge
GPQA Diamond (Epoch AI)88.1%90.9%
Maths
AIME-style maths (OTIS mock)98.3%71.1%
Chess puzzles33.0%17.0%
Surface Evolver Bench28.1%55.0%
Agents
APEX-Agents51.6%37.7%
DTBench88.2%78.9%
LMCA35.8%33.7%
Mystery game puzzles17.0%8.0%

Tests at least two of these models have taken. Bold rows are the core tests.

This page as a chartDownload PNG