ModelLab
ModelsCompare
ModelsClaude Haiku 4.6
A

Claude Haiku 4.6

Anthropic

Sub-second responses at near-frontier quality.

Small / fastVision
Lab page

Released

Feb 11, 2026

Context

250K

Pricing

$0.80/$4.00

per 1M tok

Best at

Fastest Claude

Performance

Benchmarks

Chatbot Arena
1395#16/17

Crowdsourced head-to-head chat preference Elo from LMArena. Captures perceived helpfulness and vibe across real-world prompts.

SWE-bench Verified
44.8#17/17

Share of real GitHub issues a model can autonomously resolve end-to-end (with tests passing). The de-facto agentic coding benchmark.

AIME 2025
80.1#16/16

American Invitational Mathematics Examination — competition math that rewards deep, multi-step reasoning. Reported as % solved.

GPQA Diamond
71.2#16/17

Google-proof graduate-level science Q&A (physics, biology, chemistry). PhD-level questions that resist web lookup.

MMLU-Pro
75.4#16/17

Harder, 10-way multiple-choice version of MMLU across 14 academic and professional domains. Breadth-of-knowledge signal.

Aider Polyglot
61.0#17/17

Editing a real codebase across multiple languages. Measures practical, instruction-following coding skill (not just generation).

OSWorld
15.5#15/16

Computer-use / agentic benchmark: completing real desktop OS tasks (apps, files, browsers). The leading autonomy metric.

Value score: 50/100

Quality-per-dollar blend of Chatbot Arena Elo against API price. Free / open models are scored against a floor.

API pricing

Input$0.80per 1M tokens
Output$4.00per 1M tokens
1M tokens blended$4.80in + out

Capabilities

  • Fastest Claude
  • Near-frontier
  • Edge-ready
TextVision

Closest rivals

By Chatbot Arena Elo

  • OA

    GPT-5.1 mini

    OpenAI

    1402
  • Q

    Qwen3-235B

    Qwen

    1408
  • ∞

    Llama 4 Maverick

    Meta

    1417

More from

Anthropic

A

Claude Opus 4.8

Top of the LLM Stats overall board; leading on deep coding.

A

Claude Sonnet 4.6

The model most developers actually ship on.

Data last checked May 20, 2026 (2mo ago)

ModelLab

An independent dashboard for comparing frontier AI models. Benchmark scores are drawn from public model cards, papers, and leaderboards. Always verify against the original source before making decisions.

Navigate

  • All models
  • Compare
  • About the data

Sources

  • LMArena ↗
  • SWE-bench ↗
  • LiveBench ↗

Data snapshot last checked June 17, 2026.

Not affiliated with any AI lab. Scores are approximations.