readable AI benchmarks (simplified)

readable AI benchmarks

MiniMax

MiniMax-M2

reasoning · open weights · Oct 26, 2025

MiniMax-M2 has a Quality Score of 27.7, ranking 278th among 551 scored models. Per 1M tokens, pricing is $0.300 input and $1.20 output. It accepts text input, outputs text, and has a 204,800 token context window. Its Reliability Score is 26.7, ranking 350th among 553 scored models, below average (total average: 35.6).

Quality Score27.7coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Scorenot available
Factual reliability26.7
Cache Discountnot available

Model specification

Reasoning
reasoning
Input modalities
text
Output modalities
text
Context window
204,800 tokens
Weights
open weights

Token prices USD per 1M tokens

Input
$0.300
Output
$1.20
Cached Input
not available
Cache write
not available
Cost per task
not available

Capability

Intelligence
18.6
Coding
not available
Agentic
not available
Omniscience
-46.5
Correct
23.2%
Blended price
not available

Answer outcomes

Fully graded outcomes (Correct + Incorrect): 93.0%

Correct 23.2%Incorrect 69.8%Partial / not attempted 7.0%

Artificial Analysis benchmarks

Humanity’s Last Exam
14%
GPQA Diamond
78%
CritPt
1%
AA-Omniscience
27%
AA-LCR
64%

Similar models

Support me! Patreon