readable AI benchmarks (simplified)

readable AI benchmarks

Xiaomi

MiMo-V2-Pro

reasoning · closed weights · Mar 18, 2026

MiMo-V2-Pro has a Quality Score of 48.2, ranking 103rd among 551 scored models. It accepts text input, outputs text, and has a 1M token context window. Its Reliability Score is 52.3, ranking 89th among 553 scored models, above average (total average: 35.6).

Quality Score48.2coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Scorenot available
Factual reliability52.3
Cache Discountnot available

Model specification

Reasoning
reasoning
Input modalities
text
Output modalities
text
Context window
1M tokens
Weights
closed weights

Token prices USD per 1M tokens

Input
not available
Output
not available
Cached Input
not available
Cache write
not available
Cost per task
not available

Capability

Intelligence
28.6
Coding
not available
Agentic
not available
Omniscience
4.6
Correct
26.6%
Blended price
not available

Answer outcomes

Fully graded outcomes (Correct + Incorrect): 48.6%

Correct 26.6%Incorrect 22.0%Partial / not attempted 51.4%

Artificial Analysis benchmarks

Humanity’s Last Exam
30%
GPQA Diamond
87%
CritPt
0%
AA-Omniscience
52%
AA-LCR
68%

Similar models

Support me! Patreon