Unverified50% confidenceBenchmarkExact time
When all models are scored only on the remaining four tracks, the lab's model's composite score becomes 0.678, ranking it 6th.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/5/2026
First Seen
Valid until: 10/19/2026
Sources
Related Entities
Related Claims
Unverified在MoE模型中每个token只激活少量Expert（通常2-4个，Top-K路由），实际计算量可能仅相当于6-7B的Dense模型70% similarUnverifiedThe lab that published HakemBench ranked its own model 7th with a composite score of 0.660.64% similarUnverifiedOn the legacy codebase test leaderboard, most models score only in the teens to twenties; Sol ranks fourth based on one recorded entry (which is not the same result as this test).64% similarUnverified跑分排名不等于所有场景的实际表现，Terra跑分接近5.5但游戏任务中5.5完成度略高64% similarUnverifiedThe final parameter count of the model after training was 13,693,824.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/975451API
curl https://kongchang.com/api/v1/knowledge/claims/975451MCP
get_claim(id=975451)