MiMo-V2-Flash (Reasoning) — benchmark results

MiMo-V2-Flash evaluated with reasoning enabled. Provider: Xiaomi. Released 2026-01-01. Access: Open.

Unified ELO 1763 ± 34, rank #173 of 1776 rated models, from 60 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
AA AIME 202596.33Accuracy (%)97.8
AA LiveCodeBench86.77Pass@1 (%)97.5
AA TAU-2 Bench95.03Accuracy (%)93.8
AA MMLU-Pro84.34Accuracy (%)89.2
UGI - Natural Intelligence43.12NatInt Score88.3
UGI Leaderboard48UGI Score86.3
UGI - Writing44.85Writing Score85.8
AA Omniscience - Software Engineering (SWE) - Julia36Accuracy (%)84.6
AA CritPt4.29Accuracy (%)84.1
AA GPQA Diamond84.65Accuracy (%)83
AA Humanity's Last Exam21.13Accuracy (%)81.4
AA Global-MMLU-Lite - Korean87.58Accuracy (%)78.3

Interactive version: theaggregate.ai/model?slug=mimo-v2-flash-reasoning · How the rankings work · Data refreshed daily, snapshot 2026-07-22.