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

Anthropic · Active

Claude Opus 5.5

claude-opus family · launched 2026-09-22

MultimodalReasoningTools

AITopic score82.1#3 overall

Claude model for long-running agentic coding and knowledge work

Evidence coverage100%9 evaluations · 3 institutions

Context / maximum output1M / 128ktokens

Cache / input / output$0.2 · $4 · $20USD per million tokens

Value / freshness54.8 / 87relative value · release freshness

Product profile

What this model supports

Inputtext, image

Outputtext

Knowledge cutoff2026-06

WeightsProprietary / hosted

Capability profile

Strengths by domain

Coding85.72 public results

Research & reasoning83.92 public results

Professional work77.32 public results

Knowledge & instruction77.92 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 · CodingLiveBench96.30 scoreReading 96.3

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

AIHOT · CodingAIHOT75.00 scoreReading 75.0

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

Research & reasoning2 results

LiveBench 2.0 · ResearchLiveBench92.20 scoreReading 92.2

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 · ResearchAIHOT75.60 scoreReading 75.6

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 · ProfessionalLiveBench82.10 scoreReading 82.1

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 · ProfessionalAIHOT72.50 scoreReading 72.5

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

Knowledge & instruction2 results

LiveBench 2.0 · KnowledgeLiveBench85.00 scoreReading 85.0

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 · KnowledgeAIHOT70.70 scoreReading 70.7

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

Human preference & indices4 results

LiveBenchLiveBench85.99 scoreReading 86.0

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 TextLMArena1,512.3 EloReading 82.1

Direct LMArena text leaderboard result.

AA IndexArtificial Analysis70.93 indexReading 76.4

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 leaderboardAIHOT74.10 scoreReading 74.1

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