Unverified50% confidenceBenchmarkExact time
On the WikiRacing task, Jev scored a perfect 30/30, while CLM-8B scored 26/30.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/24/2026
First Seen
Valid until: 12/23/2026
Sources
Related Entities
Related Claims
UnverifiedUsing the Qwen3-27B model on the wikitext-2 dataset with fp32 reference logits as a baseline for KL divergence measurement, the median KLD dropped from 0.0023 to 0.000001, an approximately 2300-fold improvement in precision.58% similarUnverified评测者认为通义千问3.6 27B是30B级别中对高考数学题表现最好的模型57% similarUnverifiedUnder an 18k character budget, anchored hybrid retrieval achieved 36.18% accuracy, BM25 achieved 35.98%, while the best direct planner-guided method reached only 34.19%.56% similarUnverifiedOn the Berkeley Function Calling Leaderboard v4, Jev scored 99.2% and CLM-8B scored 95.2%.55% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/946810API
curl https://kongchang.com/api/v1/knowledge/claims/946810MCP
get_claim(id=946810)