Skip to content

Xiaomi Proprietary Released Mar 18, 2026 Updated

MiMo-V2-Pro

ToolsGuide Scores, rankings, test results and price.

Model summary

  • Text #74 / 419

    411 / 1,000

    ToolsGuide Score· votes only

  • Coding #83 / 151

    301 / 1,000

    ToolsGuide Score· votes 307, tests 297

  • Price per 1M tokens

    No listed price

Summary

MiMo-V2-Pro is Xiaomi's model, released Mar 18, 2026. It's ranked in 2 categories and does best at text: #74 of 419, with a ToolsGuide Score of 411 against a median of 252.

It also ranks #83 of 151 for coding (301).

Its text score uses votes only, because it has published fewer than two of the tests used for that category.

It has published results on 7 tests.

Specifications

Creator
Xiaomi
Licence
Proprietary
Released
Mar 18, 2026
Context window
–
Input price
–
Output price
–
Tests reported
7
Settings ranked
MiMo-V2-Pro

Model comparison

Against the ten best text models.

Text score

ToolsGuide Score out of 1,000 · Higher is better

Coding score

ToolsGuide Score out of 1,000 · Higher is better

Input price

USD per 1M input tokens · Lower is better

Leaderboards

Where MiMo-V2-Pro sits among the top 20 in each category.

Text

#74 of 419 · ToolsGuide Score out of 1,000, where 1,000 is a flawless model

Full text leaderboard →

Coding

#83 of 151 · ToolsGuide Score out of 1,000, where 1,000 is a flawless model

Full coding leaderboard →

By task

Scored from votes on each kind of prompt alone, on the same 1,000-point scale.

Against its nearest rivals

Text prompts by kind · ToolsGuide Score from votes · hover for values

Text

MiMo-V2-Pro · hover a bar for its rank

Coding

MiMo-V2-Pro · hover a bar for its rank

Test results

Every test MiMo-V2-Pro has a published result on, out of 100%, with its rank among the models that took it.

  • SWE-Bench Verified

    #23 / 123

    Fixing real bugs in real GitHub projects, checked by the projects' own tests.

    78.0%

    Self-reported

  • Terminal-Bench 2.0

    #25 / 54

    Getting real work done in a command-line terminal.

    57.1%

    Self-reported

  • SWE-bench Multilingual

    #24 / 50

    A multilingual benchmark for issue resolving in software engineering that covers Java, TypeScript, JavaScript, Go, Rust, C, and C++. Contains 1,632 high-quality instances carefully annotated from 2,456 candidates by 68 expert annotators, designed to evaluate Large Language Models across diverse software ecosystems beyond Python.

    71.7%

    Self-reported

  • Tau2 Telecom

    #8 / 37

    τ²-Bench telecom domain evaluates conversational agents in a dual-control environment modeled as a Dec-POMDP, where both agent and user use tools in shared telecommunications troubleshooting scenarios that test coordination and communication capabilities.

    96.8%

    Self-reported

  • Claw-Eval

    #10 / 14

    Claw-Eval tests real-world agentic task completion across complex multi-step scenarios, evaluating a model's ability to use tools, navigate environments, and complete end-to-end tasks autonomously.

    61.5%

    Self-reported

  • DeepSearchQA

    #6 / 12

    DeepSearchQA is a benchmark for evaluating deep search and question-answering capabilities, testing models' ability to perform multi-hop reasoning and information retrieval across complex knowledge domains.

    86.7%

    Self-reported

  • PinchBench

    #6 / 8

    PinchBench evaluates coding agents on real-world agentic coding tasks, measuring both best-case and average performance across complex software engineering scenarios.

    81.0%

    Self-reported