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

Moonshot AI · Active

Kimi K3

kimi-k3 family · launched 2026-07-16

MultimodalReasoningToolsStructuredOpen weights

AITopic score66.3#37 overall

Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work

Evidence coverage100%9 evaluations · 3 institutions

Context / maximum output1M / 65.5ktokens

Cache / input / output$0.3 · $3 · $15USD per million tokens

Value / freshness48.5 / 76relative value · release freshness

Product profile

What this model supports

Inputtext, image

Outputtext

Knowledge cutoffNot disclosed

WeightsOpen weights

Capability profile

Strengths by domain

Coding59.72 public results

Research & reasoning76.72 public results

Professional work64.22 public results

Knowledge & instruction73.02 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

AIHOT · CodingAIHOT60.00 scoreReading 60.0

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

LiveBench 2.0 · CodingLiveBench59.30 scoreReading 59.3

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

Research & reasoning2 results

LiveBench 2.0 · ResearchLiveBench90.70 scoreReading 90.7

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 · ResearchAIHOT62.60 scoreReading 62.6

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 · ProfessionalLiveBench64.38 scoreReading 64.4

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 & instruction2 results

LiveBench 2.0 · KnowledgeLiveBench79.00 scoreReading 79.0

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

AIHOT · KnowledgeAIHOT66.90 scoreReading 66.9

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

Human preference & indices4 results

LiveBenchLiveBench69.50 scoreReading 69.5

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

Arena TextLMArena1,475.7 EloReading 66.3

Direct LMArena text leaderboard result.

AA IndexArtificial Analysis67.28 indexReading 65.2

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 leaderboardAIHOT62.70 scoreReading 62.7

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