Claude Opus 4.7

Anthropic·claude-opus-4-7

Rank · overall#15

Score76.2

Benchmark scores

12 benchmarks

SWE-bench Verified82%

% Resolved · 2026-04-16

Terminal-Bench 2.168.9%

Accuracy · May 1, 2026 · ± 1.4

Chatbot Arena (Coding)1559Coding Elo

ARC-AGI75.8%

Score

Arena Agent8.17%

Net Improvement · ± 1.43

WebDev Arena1558WebDev Elo · ± 6

Stratix Cup22.7Tournament score

FrontierMath (Tier 4)31.7%

Accuracy · ± 7.4

MCP Atlas79.1Score

SkillsBench61.2Score

MathArena Apex40.6%

Accuracy

BrowseComp79.3%

Accuracy

2 agents

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

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