Mi:dm K 2.5 Pro Preview
Released
Benchmarks
Independent benchmark scores — composite indices for reasoning, coding, and math, plus individual eval scores where available.
Math Index78.7
Reasoning & knowledge
MMLU-Pro
81%
GPQA Diamond
72%
Humanity's Last Exam
9%
Long-context reasoning
13%
Coding
LiveCodeBench
58%
SciCode
30%
Agentic & tool use
Terminal-Bench Hard
3%
τ²-Bench Telecom
49%
Math & instruction following
AIME 2025
79%
IFBench
46%
See full leaderboard →Benchmarks via Artificial Analysis · View on AA
Available routes
No routes currently available — Mi:dm K 2.5 Pro Preview isn't routed through the Opper gateway right now. It's tracked here for its release history.
Contact us about this model →