BenchLeader
Korea TelecomReasoning modelAuto-detected

Mi:dm K 2.5 Pro

Best configuration ranks #448 of 610 on the BenchLeader Index at 43.0 ±6.3.

Blended price
Output speed
First answer
Context
128k
How it scores by categoryDashed line = average model (50). One step of 15 = one standard deviation.
  1. Overall index43
  2. Agents & tools36
  3. Knowledge36
  4. Instruction following50
  5. Long context29
  6. Composite43

Benchmark results

One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.

Reasoning

BenchmarkdefaultSource
GPQA Diamond (AA)not in index70.1%#284Artificial Analysis
Humanity's Last Exam (AA)not in index8.1%#281Artificial Analysis

Agents & tools

Knowledge

BenchmarkdefaultSource
AA-Omniscience-59.2#383Artificial Analysis

Instruction following

BenchmarkdefaultSource
IFBench49.3%#175Artificial Analysis

Long context

BenchmarkdefaultSource
AA-LCR9.0%#397Artificial Analysis

Composite

BenchmarkdefaultSource
AA Intelligence Index11.0#297Artificial Analysis

See also

Data as of 9 Sept 2026. Compare with another model.