Unverified50% confidenceBenchmarkExact time
On the held-out compound recipe test set, the LoRA fine-tuned model caught 66%, while the base Qwen3.5-4B model caught 78%.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/18/2026
First Seen
Valid until: 1/16/2027
Sources
Related Entities
Related Claims
UnverifiedOn "continuation of previous operation" type utterances, Qwen3.6-35B-A3B achieved an accuracy of 86.3%, while the 4B and 8B models achieved only 70.4%.75% similarUnverifiedOn Qwen3-8B, after the second round of the loop selected 3 new skills, model performance improved from 64.3% to 66.3%.74% similarVerifiedQwen3.5's parameter activation rate is 4.3%, while DeepSeek V3's 671B model has an activation rate of 5.5%.74% similarUnverifiedTesting with the Qwen model yielded consistent conclusions, with the token approach achieving 67.0% accuracy versus 64.8% for real data.73% similarUnverifiedThe Q3_XXS model paired with an F16 KV cache scores approximately 80% on the needle test, while Q3_K_XL paired with a kvarn3 KV cache scores close to 100%.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1060642API
curl https://kongchang.com/api/v1/knowledge/claims/1060642MCP
get_claim(id=1060642)