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
xAI · Active

Grok 4.5

grok family · launched 2026-07-08

MultimodalReasoningToolsStructured
AITopic score56.8#70 overall

xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk

Evidence coverage95%5 evaluations · 2 institutions
Context / maximum output500k / 500ktokens
Cache / input / output$0.3 · $2 · $6USD per million tokens
Value / freshness48.7 / 75relative value · release freshness
Product profile

What this model supports

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

Strengths by domain

Coding—1 public results
Research & reasoning—1 public results
Professional work—1 public results
Knowledge & instruction—1 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 · CodingLiveBench94.30 scoreReading 94.3

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 · ResearchLiveBench87.20 scoreReading 87.2

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 · ProfessionalLiveBench55.75 scoreReading 55.8

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 2.0Open evidence

Knowledge & instruction1 results

LiveBench 2.0 · KnowledgeLiveBench85.90 scoreReading 85.9

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

LiveBenchLiveBench70.06 scoreReading 70.1

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

Configuration: LiveBench 2.0Open evidence
AA IndexArtificial Analysis64.49 indexReading 56.8

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

Configuration: Grok 4.5Open evidence
Arena TextLMArena1,447.6 EloReading 56.8

Direct LMArena text leaderboard result.

Open evidence
Same builder

More from xAI