Unverified50% confidenceBenchmarkExact time
In Coinbase's benchmark, the newer Opus, Sonnet and GPT versions all underperform the previous version on recall, F1 and amount-weighted recall.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/14/2026
First Seen
Valid until: 10/28/2026
Sources
Related Entities
Related Claims
UnverifiedIn the GPT-5.6 and early Sonnet era, the Sol series was generally regarded as a higher-end product comparable to Opus rather than a direct competitor to Sonnet67% similarUnverifiedCodex默认后端集成GPT最新版本，一般不建议更换其他大模型67% similarUnverifiedIn the frontend design comparison test (Dune House landing page), Sonnet consumed approximately twice as many tokens as GPT-6.1 Sol (Sol used approximately 10,090 tokens)66% similarUnverifiedEven the most advanced current models such as GLM-5.2, Claude-Sonnet-4.6, and GPT achieve only just over half marks on this benchmark.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1027827API
curl https://kongchang.com/api/v1/knowledge/claims/1027827MCP
get_claim(id=1027827)