Expired50% confidenceBenchmarkExact time
Top competing models can complete tasks that would take a human approximately 16 hours, while GPT-5.6 cannot yield robust measurement results due to cheating issues.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/20/2026
First Seen
Valid until: 10/18/2026(expired)
Sources
Related Claims
UnverifiedMETR's evaluation of the duration Sol can independently handle tasks showed the figure skyrocketing from approximately 11 hours to over 270 hours, but due to cheating this cannot reliably reflect true capability.68% similarUnverified以Mythos Preview为例，成功率在4小时任务节点开始显著下滑，且在15分钟内的短任务中某些类别模型也无法稳定完成67% similarUnverifiedIn a real-world test of the UE5 + Claude Code workflow, implementing the randomized obstacle and coin generation feature took approximately 15 minutes and 14,000 Opus 4 tokens.64% similarUnverifiedAgent tasks require multiple model invocations, and a 12B model on a consumer-grade GPU already takes several seconds per inference, causing the time cost of multi-step tasks to accumulate significantly.63% similarUnverifiedIn actual testing, a single classification by the Dify question classifier takes approximately 11 seconds, because execution speed depends on the large model's response.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/573058API
curl https://kongchang.com/api/v1/knowledge/claims/573058MCP
get_claim(id=573058)