Unverified50% confidenceBenchmarkExact time
On the GDPVal benchmark, Opus 5.5 scored 1846 and Astra scored 1542.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/7/2026
First Seen
Valid until: 1/5/2027
Sources
Related Entities
Related Claims
UnverifiedOn GDP Val 2.1, Opus 5.5 achieved an ELO score of 1846, Fable 5.1 scored 1735, and Astra scored 1542.77% similarUnverifiedClaude Opus 5.5 scored 1846 points in the GDPval knowledge work benchmark, compared to Sonnet 5.1's score of 1735 points.69% similarUnverifiedClaude Opus 5 scored 1861 on the knowledge work benchmark GDPval, above the human average.68% similarUnverifiedIn the GDP PDF evaluation, GPT-6.1 Sol scored 32.0%, Astra scored 32.2%, and Opus 5.5 with a fallback mechanism scored 28.8%.68% similarUnverifiedClaude Sonnet 5 在 GDP-WoW 基准上得 1619 分，反超 Opus67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/984121API
curl https://kongchang.com/api/v1/knowledge/claims/984121MCP
get_claim(id=984121)