Translate
Independent model intelligence

Find the right AI model,
not just the loudest one.

Compare current model capability, context, modalities, public preference and API economics in one continuously refreshed decision surface.

LiveBench 2.0 LMArena models.dev OpenRouter AIHOT cross-check
Back to leaderboard
Xiaomi · Active

MiMo-V2.6-Pro

mimo family · launched 2026-09-22

MultimodalReasoningToolsStructuredOpen weights
AITopic score72.8#20 overall

MiMo-V2.6-Pro is the flagship foundation model developed by Xiaomi. Built at a scale of over 1T parameters, it is designed to push the ceiling of capability for the most demanding...

Evidence coverage100%8 evaluations · 3 institutions
Context / maximum output1M / 131.1ktokens
Cache / input / output$0.004 · $0.44 · $0.87USD per million tokens
Value / freshness85.4 / 87relative value · release freshness
Product profile

What this model supports

Inputtext, image, audio, video
Outputtext
Knowledge cutoffNot disclosed
WeightsOpen weights
Capability profile

Strengths by domain

Coding72.52 public results
Research & reasoning79.62 public results
Professional work65.02 public results
Knowledge & instruction76.71 public results
Behind the score

Every result has a source

Raw results and standardized readings are shown together. Missing tests add neither points nor penalties.

Coding2 results

LiveBench 2.0 · CodingLiveBench81.50 scoreReading 81.5

Imported from LiveBench 2.0. The published 0–100 score is used directly; it is not z-score normalized.

Configuration: LiveBench 2.0, AIHOT aggregateOpen evidence
AIHOT · CodingAIHOT63.50 scoreReading 63.5

Imported from AIHOT aggregate leaderboard. The published 0–100 score is used directly; it is not z-score normalized.

Configuration: LiveBench 2.0, AIHOT aggregateOpen evidence

Research & reasoning2 results

LiveBench 2.0 · ResearchLiveBench79.60 scoreReading 79.6

Imported from LiveBench 2.0. The published 0–100 score is used directly; it is not z-score normalized.

Configuration: LiveBench 2.0, AIHOT aggregateOpen evidence
AIHOT · ResearchAIHOT59.60 scoreReading 59.6

Imported from AIHOT aggregate leaderboard. The published 0–100 score is used directly; it is not z-score normalized.

Configuration: LiveBench 2.0, AIHOT aggregateOpen evidence

Professional work2 results

LiveBench 2.0 · ProfessionalLiveBench65.83 scoreReading 65.8

Imported from LiveBench 2.0. The published 0–100 score is used directly; it is not z-score normalized. Professional = long-agentic, browser, data-analysis and design average.

Configuration: LiveBench 2.0, AIHOT aggregateOpen evidence
AIHOT · ProfessionalAIHOT64.10 scoreReading 64.1

Imported from AIHOT aggregate leaderboard. The published 0–100 score is used directly; it is not z-score normalized.

Configuration: LiveBench 2.0, AIHOT aggregateOpen evidence

Knowledge & instruction1 results

LiveBench 2.0 · KnowledgeLiveBench76.70 scoreReading 76.7

Imported from LiveBench 2.0. The published 0–100 score is used directly; it is not z-score normalized. Knowledge uses the published LiveBench research suite.

Configuration: LiveBench 2.0, AIHOT aggregateOpen evidence

Human preference & indices4 results

Arena TextLMArena1,491.4 EloReading 72.8

Direct LMArena text leaderboard result.

Open evidence
LiveBenchLiveBench71.59 scoreReading 71.6

Imported from LiveBench 2.0. The published 0–100 score is used directly; it is not z-score normalized.

Configuration: LiveBench 2.0, AIHOT aggregateOpen evidence
AA IndexArtificial Analysis68.84 indexReading 70.0

Imported from Artificial Analysis. The published 0–100 score is used directly; it is not z-score normalized.

Configuration: LiveBench 2.0, AIHOT aggregateOpen evidence
AIHOT aggregate leaderboardAIHOT62.30 scoreReading 62.3

Imported from AIHOT aggregate leaderboard. The published 0–100 score is used directly; it is not z-score normalized.

Configuration: LiveBench 2.0, AIHOT aggregateOpen evidence
Same builder

More from Xiaomi