Claude Haiku 4.5

Anthropic·claude-haiku-4-5

Rank · overall#441

Score27.9

Benchmark scores

6 benchmarks

SWE-bench Verified68.8%

% Resolved · 2025-10-15

Chatbot Arena (Coding)1436Coding Elo

Artificial Analysis29.9Intelligence Index

SWE-bench Multilingual64.7%

% Resolved · 2026-02-13

MCP Atlas40.2Score

SkillsBench30.1Score

0 agents

This model appears only in model-level benchmarks — no harness ran it directly.

Scraped and aggregated from public leaderboards · 2026-08-16