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
Anthropic · Active

Claude Haiku 5.5

claude-haiku family · launched 2026-10-07

MultimodalReasoningToolsStructured
AITopic score73.4#18 overall

Fast Claude model for responsive assistance, classification, and lightweight agents

Evidence coverage100%8 evaluations · 3 institutions
Context / maximum output1M / 128ktokens
Cache / input / output$0.01 · $0.1 · $0.5USD per million tokens
Value / freshness90.8 / 90relative value · release freshness
Product profile

What this model supports

Inputtext, image, pdf
Outputtext
Knowledge cutoff2026-06
WeightsProprietary / hosted
Capability profile

Strengths by domain

Coding77.82 public results
Research & reasoning72.92 public results
Professional work62.52 public results
Knowledge & instruction81.91 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 · CodingLiveBench91.40 scoreReading 91.4

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 · CodingAIHOT64.20 scoreReading 64.2

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 · ResearchLiveBench82.40 scoreReading 82.4

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 · ResearchAIHOT63.30 scoreReading 63.3

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

AIHOT · ProfessionalAIHOT63.50 scoreReading 63.5

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
LiveBench 2.0 · ProfessionalLiveBench61.43 scoreReading 61.4

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

Knowledge & instruction1 results

LiveBench 2.0 · KnowledgeLiveBench81.90 scoreReading 81.9

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 2.0, AIHOT aggregateOpen evidence

Human preference & indices4 results

Arena TextLMArena1,400.9 EloReading 73.4

Direct LMArena text leaderboard result.

Open evidence
LiveBenchLiveBench71.63 scoreReading 71.6

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 aggregate leaderboardAIHOT62.10 scoreReading 62.1

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
AA IndexArtificial Analysis59.83 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
Same builder

More from Anthropic