Claude Opus 5

Anthropic·claude-opus-5

Rank · overall#1

Score96.5

Benchmark scores

8 benchmarks

SWE-bench Verified97%

% Resolved · 2026-07-24

Chatbot Arena (Coding)1566Coding Elo

Artificial Analysis63.1Intelligence Index

ARC-AGI90.4%

Score

Arena Agent12.19%

Net Improvement · ± 1.45

WebDev Arena1663WebDev Elo · ± 9

FrontierMath (Tier 4)73.2%

Accuracy · ± 7

MCP Atlas85.8Score

0 agents

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

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