Xiaomi · mit

MiMo-V2-Flash

MiMo-V2-Flash by Xiaomi appears in 1 source with Reasoning at 38.43. Best read for Code quality, Math, Open weights.

CreatorXiaomi

Release date2025-12-16

Knowledge cutoffNot published

ContextUnknown

Input priceUnknown

Output priceUnknown

Modalitytext

CountryCN

Metrics

All source-backed metrics

Open in leaderboard

LLM Stats Rank64ranking · source_rank

Reasoning38.43reasoning · index_reasoning

Math37.86math · index_math

Coding22.78coding · index_code

Research15.99research · index_search

Vision18.51multimodal · index_vision

Tool calling9.27tool_calling · index_tool_calling

Long context21.89long_context · index_long_context

Finance38.17domain · index_finance

Legal38.15domain · index_legal

Healthcare37.92domain · index_healthcare

GPQA83.7 %reasoning · gpqa_score

AIME 202594.1 %math · aime_2025_score

SWE-bench Verified73.4 %coding · swe_bench_verified_score

Code Arena793.45 %coding · coding_arena_score

Humanity Last Exam22.1 %reasoning · hle_score

BrowseComp58.3 %research · browsecomp_score

Terminal Bench30.5 %coding · terminal_bench_score

Parameters309,000,000,000 paramsmodel · params

Evidence

Citations and source overlap

LLM StatsPublic full LLM leaderboard advanced explorer snapshot, including ranking, benchmark indexes, pricing, speed, context, license, and model metadata.Retrieved 2026-06-01

FAQ

How should I read this profile?

Treat this as a source-backed model dossier, not an EvalKit-run verification. The public values are replicated from linked sources and kept source-scoped.

Is MiMo-V2-Flash verified by EvalKit?

No. EvalKit currently shows 0 verified rows until real run evidence exists.

Why can metrics disagree?

Different sources test different tasks, dates, prompts, and aggregation methods. EvalKit keeps those differences visible instead of merging them into a fake universal score.