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
Mistral AI · Active

mistral-large-4

mistral-large family · launched 2026-10-06

MultimodalReasoningToolsStructured
AITopic score55.6#70 overall

Mistral's 1T-parameter multimodal MoE for reasoning, coding, and agentic work

Evidence coverage95%5 evaluations · 2 institutions
Context / maximum output524.3k / 262.1ktokens
Cache / input / output$0.0732 · $0.71 · $2.19USD per million tokens
Value / freshness61.3 / 100relative value · release freshness
Product profile

What this model supports

Inputtext, image
Outputtext
Knowledge cutoffNot disclosed
WeightsProprietary / hosted
Capability profile

Strengths by domain

Coding60.01 public results
Research & reasoning83.91 public results
Professional work40.51 public results
Knowledge & instruction28.11 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.

Coding1 results

LiveBench 2.0 · CodingLiveBench60.00 scoreReading 60.0

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

Configuration: LiveBench 2.0Open evidence

Research & reasoning1 results

LiveBench 2.0 · ResearchLiveBench83.90 scoreReading 83.9

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

Configuration: LiveBench 2.0Open evidence

Professional work1 results

LiveBench 2.0 · ProfessionalLiveBench40.48 scoreReading 40.5

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 2.0Open evidence

Knowledge & instruction1 results

LiveBench 2.0 · KnowledgeLiveBench28.10 scoreReading 28.1

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 2.0Open evidence

Human preference & indices3 results

Arena TextLMArena1,430.0 EloReading 55.6

Direct LMArena text leaderboard result.

Open evidence
AA IndexArtificial Analysis63.08 indexReading 51.1

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

Configuration: LiveBench 2.0Open evidence
LiveBenchLiveBench47.70 scoreReading 47.7

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

Configuration: LiveBench 2.0Open evidence
Same builder

More from Mistral AI