Unverified50% confidenceBenchmarkExact time
In a speculative decoding test using Qwen2.5 0.5B as the draft model proposing 4 tokens at a time, the overall draft acceptance rate was 32.9% for serial processing and 37.1% for concurrent processing.
1
Sources
50%
Confidence
Long-term
Relevance
10/11/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedAfter a developer applied abliteration to Qwen3-VL-4B-Instruct, the HarmBench compliance rate reached 100%, compared to only 30.8% for the original model.75% similarUnverifiedAccording to the SWE-Bench Verified benchmark, Qwen 2.5 Coder 32B achieves a coding ability score of 61.773% similarUnverifiedThe Qwen3.6 35B model contains 256 experts, with each token activating only 8 routed experts and 1 shared expert, resulting in approximately 3B activated parameters during actual inference.71% similarUnverified3,189 successful rollouts were collected from Qwen3.8-27B for supervised fine-tuning (imitation learning), and performance stagnated at 47.5%, below the results of two rounds of RL training.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1000270API
curl https://kongchang.com/api/v1/knowledge/claims/1000270MCP
get_claim(id=1000270)