Unverified50% confidenceBenchmarkExact time
In the first round of tests (23 synthetic cases × 3 runs), qwen2.5:1.5b achieved only a 30% correct-judgment rate and qwen2.5:7b only 46%, both failing; qwen2.5:7b incorrectly judged "covered" in 14% of cases.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/19/2026
First Seen
Valid until: 1/17/2027
Sources
Related Entities
Related Claims
UnverifiedUsing Qwen3-14B to generate risk exam papers yielded only 5/25 passages with clear signals, and only after switching to stricter prompts and Qwen3-32B were 21 passages obtained.79% similarUnverifiedIn 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.77% similarUnverifiedQwen3-1.7B's overall causal faithfulness is only 54.8%, far below that of Qwen3-4B.77% similarUnverifiedThe author noted that other models previously tested, such as 35B and 3B variants, actually performed worse than the Q2 version of Qwen3 27B on the Kanban task.77% similarUnverifiedQwen3 27B's scores on several programming and agent benchmarks surpassed those of Claude Opus 4.6.76% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1069624API
curl https://kongchang.com/api/v1/knowledge/claims/1069624MCP
get_claim(id=1069624)