Claude Sonnet 4.5

Anthropic·claude-sonnet-4-5

Rank · overall#256

Score41.2

Benchmark scores

6 benchmarks

SWE-bench Verified70.6%

% Resolved · 2025-09-29

Chatbot Arena (Coding)1464Coding Elo

FrontierMath (Tier 4)2.4%

Accuracy · ± 2.4

SWE-bench Multilingual67%

% Resolved · 2026-02-13

MCP Atlas59.5Score

SkillsBench36.2Score

0 agents

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

Scraped and aggregated from public leaderboards · 2026-07-22