Unverified50% confidenceFactExact time
The framework was applied to six 7-9B instruction-tuned models (three general-purpose: Mistral-7B, Phi-3.5-mini, Llama-3.1-8B; three medically adapted: BioMistral-7B, OpenBioLLM-Llama3-8B, Med42-Llama3-8B), tested on 200 real patient questions from the K-QA benchmark.
1
Sources
50%
Confidence
Long-term
Relevance
10/20/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe benchmark covers 9 models from 6 labs, including Qwen3 235B, Claude Haiku 4.5, Claude Opus 5.5, Gemini series, GPT-5.4 series, GLM-5, and Grok 4.20, of which 4 are reasoning models.69% similarUnverifiedThe test covered 8 local models: Qwen3's 0.6B, 1.7B, 4B, 8B, and 14B, as well as Gemma3's 1B, 4B, and 12B, all deployed via Ollama with thinking mode disabled.68% similarUnverifiedThe dataset covers four open-weight models — Qwen2.5-7B, Mistral-7B-v0.3, Phi-3.5-mini, and Qwen2.5-1.5B — with 30 trajectories each.68% similarUnverifiedMistral 7B证明精心训练的7B模型可以匹敌早期的13B甚至30B模型63% similarUnverified在HumanEval、MBPP、GSM8K等基准测试上，Gemma 7B的表现显著优于同参数量级的LLaMA 2 7B和Mistral 7B63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1074882API
curl https://kongchang.com/api/v1/knowledge/claims/1074882MCP
get_claim(id=1074882)