Unverified50% confidenceBenchmarkExact time
On the internal benchmark CoBench, Opus 5.5 successfully diagnoses real R&D problems approximately 56% of the time, while fully replacing Anthropic researchers would require at least 85%
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/4/2026
First Seen
Valid until: 10/18/2026
Sources
Related Entities
Related Claims
Unverified根据尼尔森诺曼集团的经典研究，仅需5名具有代表性的用户即可发现约85%的可用性问题67% similarUnverifiedAccording to Anthropic data, by May 2026 Claude was writing more than 80% of the company's code; Opus 4.5 has a 51% probability of suggesting a better next step when researchers choose a weaker direction, and the Mythos preview raises that figure to 64%.66% similarUnverifiedOn the BioMysteryBench bioinformatics task, the average problem-solving rate with occupational profiles was 46.7%, while the minimal baseline reached 56.7%, a gap of -10.0 percentage points (95% interval [-16.7, -3.3]).66% similarUnverifiedAn accuracy rate of 86% means there is still a 14% margin of error, making Articos more suitable as an early validation and directional judgment tool rather than a replacement for real user testing.65% similarUnverifiedAccording to the properties of the binomial distribution, detecting a 5% failure rate with 95% confidence requires at least approximately 60 independent runs.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/972611API
curl https://kongchang.com/api/v1/knowledge/claims/972611MCP
get_claim(id=972611)