readable AI benchmarks (simplified)

readable AI benchmarks

Kimi

Kimi K2.5 (Reasoning)

reasoning · open weights · Jan 27, 2026

Kimi K2.5 (Reasoning) has a Quality Score of 41.2, ranking 163rd among 551 scored models. Per 1M tokens, pricing is $0.600 input, $2.75 output, and $0.350 cached input. It accepts text, image, and video input, outputs text, and has a 256k token context window. Its Reliability Score is 46.3, ranking 150th among 553 scored models, above average (total average: 35.6). Its Value Score is 30.4, around average compared with the total Value average of 30.7.

Quality Score41.2coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score30.4
Factual reliability46.3
Cache Discount42%

Model specification

Reasoning
reasoning
Input modalities
text, image, video
Output modalities
text
Context window
256k tokens
Weights
open weights

Token prices USD per 1M tokens

Input
$0.600
Output
$2.75
Cached Input
$0.350
Cache write
not available
Cost per task
not available

Capability

Intelligence
23.5
Coding
not available
Agentic
not available
Omniscience
-7.3
Correct
35.2%
Blended price
$0.640

Answer outcomes

Fully graded outcomes (Correct + Incorrect): 77.8%

Correct 35.2%Incorrect 42.5%Partial / not attempted 22.2%

Artificial Analysis benchmarks

GDPval-AA v2
16%
τ³-Banking
14%
Humanity’s Last Exam
31%
GPQA Diamond
88%
CritPt
3%
AA-Omniscience
46%
AA-LCR
78%

Similar models

Support me! Patreon