Language

MiMo-V2.5-Pro

By Xiaomi, in the MiMo family.

Released
22 Apr 2026
Status
Legacy
Context
1M
Max output
—
Input per 1M tokens
—
Output per 1M tokens
—
Open weights
Yes
License
mit
Parameters
1020B, 42B active
Knowledge cutoff
—
Reasoning
Yes
Modalities
text → text

Category scores

Out of 100, from independent and third-party results only, by method category-2026-09-29.1.

Category scores
CategoryScoreRankCoverage
Knowledge & reasoning34.7Not ranked1 of 4
Human preference60.3Not ranked2 of 5

Benchmark results

Every result we hold for this model, with who ran it and where it was published.

Knowledge & reasoning

Knowledge & reasoning results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
DTBench (Decision Theory Benchmark)Accuracy (capability questions)84.5%Third party——https://conceptualreasoning.ai/dtbench via Epoch AI
Humanity's Last Exam (HLE)Accuracy48.0%Self-reported——Model Card via Hugging Face Community Evals
LMCA (Language Model Conceptual Argumentation)Correlation with expert ratings (Pearson r)0.295Third party——https://conceptualreasoning.ai/lmca via Epoch AI
MMLU-ProAccuracy68.5%Self-reported——Model Card via Hugging Face Community Evals

Scientific reasoning

Scientific reasoning results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
GPQA DiamondAccuracy66.7%Self-reported——Model Card via Hugging Face Community Evals

Human preference

Human preference results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
Code Arena: WebDev (arena.ai)Arena score (Elo scale)1477Independent—25 Sep 2026Arena
Code Arena: WebDev (arena.ai)Votes19401Independent—25 Sep 2026Arena
Text Arena (arena.ai)Arena score (Elo scale)1467Independent—25 Sep 2026Arena
Text Arena (arena.ai)Votes69225Independent—25 Sep 2026Arena

Other MiMo versions

Sources