Unverified50% confidenceBenchmarkExact time
All four agents achieved positive average relative improvements across the 25 tasks: Claude Opus 10.4%, Claude Sonnet 9.6%, Gemini 6.8%, and Codex 4.4%; the existing best results on all benchmarks were surpassed, and no academic misconduct was found in the audit stage.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/28/2026
First Seen
Valid until: 1/26/2027
Sources
Related Entities
Related Claims
UnverifiedOpus-4-8's raw capability is 10 percentage points higher than sonnet-4-6's, but its scope compliance capability is 35.6 percentage points higher.72% similarUnverifiedClaude Opus 5 achieved a pass@20 of 79.09% on ThinkingBox, with an all-20 of 47.53% (241 tasks passing consistently).70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1108392API
curl https://kongchang.com/api/v1/knowledge/claims/1108392MCP
get_claim(id=1108392)