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

xAI · Active

grok-4.7-xhigh

grok family · launched 2026-09-21

MultimodalReasoningTools

AITopic score73.0#23 overall

Grok model for agentic tool use, reasoning, coding, and live assistance

Evidence coverage100%8 evaluations · 3 institutions

Context / maximum output524.3k / 500ktokens

Cache / input / output$0.5 · $2 · $6USD per million tokens

Value / freshness61.0 / 100relative value · release freshness

Product profile

What this model supports

Inputtext, image

Outputtext

Knowledge cutoffNot disclosed

WeightsProprietary / hosted

Capability profile

Strengths by domain

Coding73.12 public results

Research & reasoning82.71 public results

Professional work65.52 public results

Knowledge & instruction74.42 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 · CodingLiveBench84.50 scoreReading 84.5

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 · CodingAIHOT61.70 scoreReading 61.7

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

Research & reasoning1 results

LiveBench 2.0 · ResearchLiveBench82.70 scoreReading 82.7

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

Professional work2 results

LiveBench 2.0 · ProfessionalLiveBench66.25 scoreReading 66.3

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 · ProfessionalAIHOT64.70 scoreReading 64.7

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

Knowledge & instruction2 results

LiveBench 2.0 · KnowledgeLiveBench86.40 scoreReading 86.4

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 · KnowledgeAIHOT62.40 scoreReading 62.4

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

LiveBenchLiveBench74.09 scoreReading 74.1

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 TextLMArena1,400.5 EloReading 73.0

Direct LMArena text leaderboard result.

AIHOT aggregate leaderboardAIHOT61.60 scoreReading 61.6

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

AA IndexArtificial Analysis60.08 indexReading 42.7

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