Unverified50% confidenceBenchmarkExact time
Claude Opus 5 achieved a pass@20 of 79.09% on ThinkingBox, with an all-20 of 47.53% (241 tasks passing consistently).
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/9/2026
First Seen
Valid until: 1/7/2027
Sources
Related Entities
Related Claims
UnverifiedQwen3.8-27B achieves a pass@20 of 89.35% and an all-20 of 7.50% in ThinkingBox.73% similarVerifiedOpus 5's pass rate at Low Effort is approximately 60%, surpassing Opus 4.8's 59% at the Max level, for which the per-task cost is as high as $13.71% similarUnverifiedClaude Opus 5.5 topped the CursorBench evaluation benchmark with a score of 57.8% (Max mode).70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/991239API
curl https://kongchang.com/api/v1/knowledge/claims/991239MCP
get_claim(id=991239)