Automated page. Written and translated automatically by AI and checked against the sources by software; no human editor. SI-IQ is an index built from public benchmark results, not an IQ test. How it works

How smart is MiMo-V2.5-Pro?

121 SI-IQ · 90% interval 108–135
Not ranked: results from fewer than 5 benchmarks; results in fewer than 3 areas; results from fewer than 2 evaluators

MiMo-V2.5-Pro is a model from Xiaomi Corp, released on Apr 23, 2026. Its SI-IQ is 121 (90% interval 108–135), estimated from 2 benchmark results by 1 evaluator.

Data as of Oct 18, 2026 · method 1.0.0

A model is ranked when its results come from at least 5 benchmarks (the two GPQA Diamond runs count as one) in at least 3 areas, from at least 2 different evaluators, and its versions are released no more than 60 days apart. This model does not meet that yet (results from fewer than 5 benchmarks; results in fewer than 3 areas; results from fewer than 2 evaluators). Its provisional estimate rests on 2 benchmark results and can change a lot when more results arrive.

Facts

Developer
Xiaomi Corp
Released
Apr 23, 2026
Access
Open weights (restricted licence)
Benchmarks used
2 benchmark results from 1 evaluator

Every benchmark result we used

Each score is one value exactly as the source published it: for Epoch AI the best of its run settings, for OpenRouter the median hosting provider (the developer's own hosting when it ran the test). “Implied SI-IQ” is the ability that this single result points to; the overall SI-IQ is their precision-weighted average.

Benchmark Area Score Implied SI-IQ Evaluated by As listed by the source Retrieved Source
GPQA Diamond (OpenRouter run) Knowledge 85.5% 120 OpenRouter xiaomi/mimo-v2.5-pro-20260422
Xiaomi · first-party provider (1 of 5 rows)
Oct 18, 2026 OpenRouter benchmark datasets · data file
τ²-bench Airline (OpenRouter run) Agents 74.4% 128 OpenRouter xiaomi/mimo-v2.5-pro-20260422
Xiaomi · first-party provider (1 of 6 rows)
Oct 18, 2026 OpenRouter benchmark datasets · data file

Human preference (Arena)

On the Arena leaderboard, where people vote between two anonymous answers, MiMo-V2.5-Pro has a rating of 1,467 (1,464–1,471) from 75,721 votes (published Oct 15, 2026). Human preference is a different measure from benchmark ability and is not part of SI-IQ. Arena (Hugging Face)

Computed with SI-IQ method version 1.0.0. Read the full methodology

Data sources: Arena leaderboard dataset on Hugging Face (CC BY 4.0); Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter (licences and changes).