The Model Index
Up to four models

gpt-oss-120b vs MiniMax-M2

On the index (GPT-4 = 100), gpt-oss-120b scores 129 and MiniMax-M2 129. 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 gpt-oss-120b
Presets
gpt-oss-120b
129113–145
WeightsOpen
ReleasedAug 2025
Price in / out$0.15 / $0.60
Context131K
Core tests taken3 of 9
MiniMax-M2
129109–149
WeightsOpen
ReleasedOct 2025
Price in / out–
Context–
Core tests taken0 of 9

gpt-oss-120b and MiniMax-M2 are too close to call (0 points apart, within the uncertainty).

Test by testthird-party results

gpt-oss-120bMiniMax-M2
0%25%50%75%100%REASONING & KNOWLEDGESimpleBenchSimpleBenchCODINGTerminal-Bench 2.0 (Terminus 2 runs)Terminal-Bench 2.0 (Terminus 2 runs)
Every result as a table
Testgpt-oss-120bMiniMax-M2
Reasoning & knowledge
SimpleBench22.1%25.0%
Coding
Terminal-Bench 2.0 (Terminus 2 runs)18.7%30.0%
Task length · METR34 sec

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

This page as a chartDownload PNG