readable AI benchmarks (simplified)

readable AI benchmarks

Korea Telecom

Mi:dm K 2.5 Pro Preview

reasoning · closed weights · Dec 11, 2025

Mi:dm K 2.5 Pro Preview does not yet have enough benchmark data for a Quality Score. It has a 128k token context window. Its Reliability Score is 18.6, ranking 479th among 553 scored models, below average (total average: 35.6).

Quality Scorenot availableQuality unavailable: missing AA Intelligence
Value Scorenot available
Factual reliability18.6
Cache Discountnot available

Model specification

Reasoning
reasoning
Input modalities
none
Output modalities
none
Context window
128k 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
not available
Coding
not available
Agentic
not available
Omniscience
-62.7
Correct
16.4%
Blended price
not available

Answer outcomes

Fully graded outcomes (Correct + Incorrect): 95.6%

Correct 16.4%Incorrect 79.1%Partial / not attempted 4.4%

Artificial Analysis benchmarks

Humanity’s Last Exam
9%
GPQA Diamond
72%
CritPt
0%
AA-Omniscience
19%
AA-LCR
15%

Similar models

Support me! Patreon