Benchmarks of Mi:dm K 2.5 Pro Preview12
BenchmarkByScoreRank
Knowledge4
Science2
Coding1
Documents1
Legacy · saturated or no longer reported4
No benchmark matches
—per task?
API price not publicprice
—output speed?
128Kcontext
Ranking?
Alternatives?
ModelScoreCostPer taskWhat changes
ModelScoreCostPer taskWhat changes
Nothing here yet.
ModelScoreCostPer taskWhat changes
ModelScoreCostPer taskWhat changes
Benchmarks
all categoriesChat & Knowledge
Humanity's Last Exam9.1#203
AA Omniscience Index-62.7#274
CritPt (physics)0#180
AA Omniscience · Accuracy16.4#210
AA-LCR (long context) 1.114.7#250
GPQA Diamond72.2#176
AIME 2025 · AA archived78.7#48
Coding
LiveCodeBench · AA archived57.6#78
Agents & Tool Use
τ²-bench · AA49.4#111
Writing & Language
IFBench (instructions)45.6#129
FAQ
How much does Mi:dm K 2.5 Pro Preview cost?›
There is no per-unit API price: API price not public.
Is Mi:dm K 2.5 Pro Preview free to use?›
There is no free API.
How good is Mi:dm K 2.5 Pro Preview, and what is it best at?›
#202 of 334 in Chat & Knowledge, #177 of 239 in Coding, #109 of 242 in Agents & Tool Use, #128 of 245 in Writing & Language.
Is Mi:dm K 2.5 Pro Preview better than Ling 3.0 Tiny?›
On Humanity's Last Exam, Mi:dm K 2.5 Pro Preview scores 9.1 vs 9.3 — about the same.
What is the context window of Mi:dm K 2.5 Pro Preview?›
128K tokens.
When was Mi:dm K 2.5 Pro Preview released? Is there a newer version?›
Released 2025-12-11. It has been superseded by Mi:dm K 2.5 Pro.
Is Mi:dm K 2.5 Pro Preview open source?›
No, Mi:dm K 2.5 Pro Preview is a closed model available through an API. The closest open-weights option here is MiMo v2.6 Pro.
Can Mi:dm K 2.5 Pro Preview read images?›
No, it accepts text only.
What is Mi:dm K 2.5 Pro Preview?›
Mi:dm K 2.5 Pro Preview is a closed language model from Korea Telecom, released Dec 2025.
What are the best alternatives to Mi:dm K 2.5 Pro Preview?›
GPT-6 Luna (better), MiMo v2.6 Pro (open weights).