Unverified50% confidenceBenchmarkExact time
FactoryDroid running the same Opus model submitted a score of 69.9%, while CloudCode scored 58%, but this data was self-reported by the vendors.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
8/16/2026
First Seen
Valid until: 11/14/2026
Sources
AI编程Harness之战：同模型慢4倍背后的真相
Related Claims
UnverifiedIn a complete AI application system, GPU inference typically accounts for only 30%–40% of total compute, with the remaining 60%–70% of the compute load borne by the CPU.59% similarUnverifiedOSWorld 2.0中模型评估仅占总得分的11.53%，且没有任何任务的模型评估占比超过50%58% similarUnverifiedIntel Arc A770M的实测LLM推理吞吐有时仅相当于同级NVIDIA独显的60%~70%58% similarUnverifiedApproximately 65% of Anthropic's product code is written with the assistance of this system57% similarUnverifiedAt this compression ratio, the model retains 74.2% top-1% accuracy57% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/759181API
curl https://kongchang.com/api/v1/knowledge/claims/759181MCP
get_claim(id=759181)