readable AI benchmarks

Xiaomi

MiMo-V2.5

reasoning · open weights · Apr 22, 2026

Quality Score37.5
Value Score38.3
Reliability45.1
Cache Discount98%

Model specification

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

Token prices USD per 1M tokens

Input
$0.140
Output
$0.280
Cached Input
$0.0028
Cached Output
not available
Cost per task
$0.010

Capability

Intelligence
38.0
Coding
56.8
Agentic
24.4
Omniscience
-9.8
Correct
16.8%
Blended price
$0.058

Answer outcomes

Correct 16.8%Incorrect 26.6%Abstained 56.7%

Artificial Analysis benchmarks

GDPval-AA v2
33%
τ³-Banking
9%
Terminal-Bench v2.1
64%
SciCode
43%
Humanity’s Last Exam
27%
GPQA Diamond
85%
CritPt
4%
AA-Omniscience
45%
AA-LCR
68%

Similar models