Claude Sonnet 5

Anthropic·claude-sonnet-5

Rank · overall#29

Score73.0

Benchmark scores

7 benchmarks

SWE-bench Verified79.8%

% Resolved · 2026-06-30

Terminal-Bench 2.174.6%

Accuracy · Jul 9, 2026 · ± 1.6

Chatbot Arena (Coding)1520Coding Elo

Arena Agent7.14%

Net Improvement · ± 2.29

WebDev Arena1540WebDev Elo · ± 8

FrontierMath (Tier 4)29.3%

Accuracy · ± 7.2

BrowseComp86.6%

Accuracy

1 agents

Per-benchmark score · composite per harness. Tap a row to open that board.

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