Coding / Agent
FreshHigh confidenceSWE-benchSWE-bench bash-only · result 2026-02-17Updated: 8/10/2026
75.6% resolved
#4 · 93th percentile
Anthropic·Claude
Claude Opus 4.6
4.6
Aliases: claude-opus-4-6, claude-4.6-opus, claude-4-6-opus
Canonical ID
anthropic-claude-opus-4-6Independent sources
2
Composite eligibility
Eligible
Public benchmark scores
Source ranks stay intact; incompatible raw scores are not added.
Conversation
StaleHigh confidenceLMArena / Chatbot ArenaText leaderboard · Aug 12, 2026Updated: 8/12/2026
Elo 1497
#5 · 99th percentile
Why it ranks here
This model has scores from 2 independent sources and is eligible for the ToolCenter composite reference.
Historical movement
Historical snapshots are available on the source score cards.