benchmarks.wiki / Public workspace

Claude 4.5 Opus (20251101) (medium)

All models · Read as JSON

These are quotations of published scores, not measurements made here. Evaluation conditions differ by row, so this is not a ranking. Different metrics must not be combined.

Recorded benchmark reports
BenchmarkScoreMetricSetupReported bySource
SWE-bench VerifiedClaude 4.5 Opus (20251101) (medium)74.4resolved (%)Verified; mini-SWE-agent; Model: claude-opus-4-5-20251101; Org: Anthropic; System: Attempts - 1; Mini: 1.16.0LeaderboardReported: 2025-11-24Verified leaderboard; 20251124_mini-v1.16.0_claude-opus-4-5-20251101Checked: 2026-09-16