readable AI benchmarks

Xiaomi

MiMo-V2.5-Pro

reasoning · open weights · Apr 22, 2026

Quality Score47.1
Value Score40.9
Reliability51.6
Cache Discount99%

Model specification

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

Token prices USD per 1M tokens

Input
$0.435
Output
$0.870
Cached Input
$0.0036
Cached Output
not available
Cost per task
$0.034

Capability

Intelligence
42.9
Coding
60.2
Agentic
29.5
Omniscience
3.3
Correct
22.4%
Blended price
$0.177

Answer outcomes

Correct 22.4%Incorrect 19.2%Abstained 58.4%

Artificial Analysis benchmarks

GDPval-AA v2
38%
τ³-Banking
10%
Terminal-Bench v2.1
65%
SciCode
50%
Humanity’s Last Exam
36%
GPQA Diamond
87%
CritPt
4%
AA-Omniscience
52%
AA-LCR
78%

Similar models