BenchLeader
Menu
Best LLMsChoose a modelLeaderboardsModelsBenchmarksProvidersReleases12
XiaomiReasoning modelCompare with another model

Mimo v2 Pro

Mimo v2 Pro is a Xiaomi proprietary reasoning model, released 18 Mar 2026. Its best configuration ranks #145 of 785 on the BenchLeader Index at 58.7 ±4.8, in the upper half. The ± is the point: 247 other configurations score within that range, so they and this one cannot be told apart on quality alone — price and speed are what separate them. It scores highest in agents & tools (70) and lowest in reasoning (49). Last measured 22 Oct 2026.

Blended price
–
Output speed
–
First answer
–
Context
1M
Full answer
–
Cost per run
–
Released
18 Mar 2026
How it scores by categoryDashed line = average model (50). One step of 15 = one standard deviation.
  1. Overall index59
  2. Reasoning49
  3. Coding53
  4. Agents & tools70
  5. Maths63
  6. Knowledge64
  7. Instruction following68
  8. Human preference63
  9. Long context59
  10. Composite62

How its index has moved

9 Sept 2026 to 19 Oct 2026
546066

The index is recomputed from scratch every day, so a line moves when a new benchmark result lands, when a publisher revises a score, or when the models it is normalised against change. Early movement usually means the score is still settling.

Benchmark results

See all LLM benchmarks. One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.

Reasoning

Benchmarknot statedSourceTrend
Arena Hard Prompts1475#74Arena (LMArena)
GPQA Diamond (AA)not in index87.0%#105Artificial Analysis
Humanity's Last Exam (AA)not in index30.4%#147Artificial Analysis
CritPt0.3%#271Artificial Analysis
CL-benchnot in index15.7%#18Epoch AI Benchmarking Hub
CL-bench Lifenot in index6.9%#15Epoch AI Benchmarking Hub

Coding

Benchmarknot statedSourceTrend
Arena Coding1503#72Arena (LMArena)
Arena WebDev1434#81Arena (LMArena)
ALE-Benchnot in index785.2#78Epoch AI Benchmarking Hub

Agents & tools

Benchmarknot statedSourceTrend
Terminal-Bench Hard40.9%#53Artificial Analysis
τ²-Bench Telecom (AA)not in index95.0%#26Artificial Analysis

Maths

Benchmarknot statedSourceTrend
Arena Maths1450#76Arena (LMArena)

Knowledge

Benchmarknot statedSourceTrend
AA-Omniscience4.6#110Artificial Analysis
AA-Omniscience: accuracynot in index26.6%#215Artificial Analysis
AA-Omniscience: non-hallucinationnot in index70.0%#43Artificial Analysis

Instruction following

Benchmarknot statedSourceTrend
IFBench68.8%#77Artificial Analysis
Arena Instruction Followingnot in index1445#71Arena (LMArena)

Human preference

Benchmarknot statedSourceTrend
Arena Text1448#81Arena (LMArena)
Arena Creative Writingnot in index1423#77Arena (LMArena)
Arena Multi-turnnot in index1466#69Arena (LMArena)
Arena Longer Queriesnot in index1467#65Arena (LMArena)

Long context

Benchmarknot statedSourceTrend
AA-LCR68.3%#235Artificial Analysis

Composite

Benchmarknot statedSourceTrend
AA Intelligence Index v4.3.228.6#132Artificial Analysis

More from Xiaomi

New this month

See also

Best for codingAll Xiaomi models

Questions people ask

What are Mimo v2 Pro's benchmark scores?
As of 24 Oct 2026, Mimo v2 Pro scores 58.7 ±4.8 on the BenchLeader Index, strongest in agents & tools (70) and weakest in reasoning (49). That rests on 11 independent benchmark results, and every score on this page links to its publisher.
How does Mimo v2 Pro rank?
Mimo v2 Pro is #145 of 785 ranked configurations on 24 Oct 2026. 247 other configurations score within its margin, so the exact position matters less than the band. The leader is Claude Opus 5.5 (max effort) at 72.6.
When was Mimo v2 Pro released?
Xiaomi released Mimo v2 Pro on 18 Mar 2026.

Data as of 24 Oct 2026. Compare with another model.

Cite as: BenchLeader, “Mimo v2 Pro: benchmarks, pricing, speed and rank”, data as of 24 Oct 2026, https://www.benchleader.com/models/mimo-v2-pro.