The Model Index
Up to four models

MiniMax-M3 vs DeepSeek-V4-Pro (Apr 2026)

On the index (GPT-4 = 100), MiniMax-M3 scores 147 and DeepSeek-V4-Pro (Apr 2026) 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 MiniMax-M3
Presets
MiniMax-M3
147131–164
WeightsOpen
ReleasedJun 2026
Price in / out$0.30 / $1.2
Context1.05M
Core tests taken4 of 9
DeepSeek-V4-Pro (Apr 2026)
147131–164
WeightsOpen
ReleasedApr 2026
Price in / out$0.90 / $1.5
Context1.05M
Core tests taken3 of 9

MiniMax-M3 and DeepSeek-V4-Pro (Apr 2026) are too close to call (0 points apart, within the uncertainty), ahead on 0 of 1 shared core tests, and costs 2.0× less.

Test by testthird-party results

MiniMax-M3DeepSeek-V4-Pro (Apr 2026)
0%25%50%75%100%REASONING & KNOWLEDGEGPQA Diamond (Epoch AI)GPQA Diamond (Epoch AI)LiveBench Data AnalysisLiveBench Data AnalysisLiveBench IFLiveBench IFLiveBench LanguageLiveBench LanguageLiveBench ReasoningLiveBench ReasoningMATHSAIME-style maths (OTIS mock)AIME-style maths (OTIS mock)LiveBench MathematicsLiveBench MathematicsChess puzzlesChess puzzlesSurface Evolver BenchSurface Evolver BenchCODINGLiveBench Agentic CodingLiveBench Agentic CodingLiveBench CodingLiveBench CodingAGENTSDTBenchDTBenchLMCALMCAMystery game puzzlesMystery game puzzles
Every result as a table
TestMiniMax-M3DeepSeek-V4-Pro (Apr 2026)
Reasoning & knowledge
GPQA Diamond (Epoch AI)90.9%90.9%
LiveBench Data Analysis76.2%74.5%
LiveBench IF57.5%62.4%
LiveBench Language76.8%78.1%
LiveBench Reasoning74.5%82.7%
Maths
AIME-style maths (OTIS mock)71.1%96.7%
LiveBench Mathematics77.0%90.7%
Chess puzzles17.0%19.0%
Surface Evolver Bench55.0%40.0%
Coding
LiveBench Agentic Coding40.7%42.6%
LiveBench Coding68.2%70.0%
Agents
DTBench78.9%90.7%
LMCA33.7%41.2%
Mystery game puzzles8.0%17.0%

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

This page as a chartDownload PNG