readable AI benchmarks (simplified)

readable AI benchmarks

Xiaomi

MiMo-V2.6-Pro

reasoning · open weights · Sep 21, 2026

MiMo-V2.6-Pro has a Quality Score of 51.5, ranking 39th among 265 scored models. Per 1M tokens, pricing is $0.435 input, $0.870 output, and $0.0036 cached input. It accepts text, image, audio, video, and pdf input, outputs text, and has a 1M token context window. Its Reliability Score is 54.2, ranking 40th among 265 scored models, above average (total average: 35.5). Its Value Score is 47.3, high compared with the total Value average of 28.9.

Quality Score51.5coverage 78.8%: missing Epoch General ECI, Coding, CursorBench 3.2, Agentic and DeepSWE v1.1
Value Score47.3
Reliability54.2
Cache Discount99%

Model specification

Reasoning
reasoning
Input modalities
text, image, audio, video, pdf
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
Cache write
not available
Cost per task
$0.133

Capability

Intelligence
46.3
Coding
not available
Agentic
not available
Omniscience
8.4
Correct
34.8%
Blended price
$0.177

Answer outcomes

Attempt rate: 61.3%

Correct 34.8%Incorrect 26.5%Abstained 38.7%

Artificial Analysis benchmarks

GDPval-AA v2
59%
SciCode
61%
Humanity’s Last Exam
49%
CritPt
27%
AA-Omniscience
54%
AA-LCR
86%

Similar models

Support me! Ko-Fi