Unverified50% confidenceFactExact time
According to Anthropic's system card, Claude Opus 5.5 reaches 89.9% accuracy on SWE-bench Pro, and the BenchLM October 2026 leaderboard also repeats this figure.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/16/2026
First Seen
Valid until: 10/30/2026
Sources
Related Entities
Related Claims
UnverifiedOpus 5.5's success rate in code review nearly doubled compared to Opus 5, and it produced no unverifiable or self-contradictory findings.71% similarUnverifiedOpus 5在Frontier-Bench上的表现超过Opus 4.8的两倍70% similarUnverifiedClaude Opus 5.5's score on the ECI benchmark surpassed competing products such as OpenAI's GPT-5.5 Pro.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1049230API
curl https://kongchang.com/api/v1/knowledge/claims/1049230MCP
get_claim(id=1049230)