Unverified50% confidenceFactExact time
The limitations of this test include: limited task scale (50 tasks, 3 trials per prompt), style versions written by a single author, length confounding between the florid and normal versions, testing only English and local models below 14B, and the perplexity check covering only three smaller Qwen models and using full-precision weights while actual inference used 4-bit quantization.
1
Sources
50%
Confidence
Long-term
Relevance
10/13/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThis test is a single-source personal test; the model designation is labeled as Qwen 3.8 27B with naming ambiguity, and details such as the actual configuration, quantization method, and generation time have not been disclosed, leaving reproducibility to be verified.72% similarUnverifiedThe research team conducted zero-shot evaluations of off-the-shelf models on 15 long-context tasks, with test subjects including Gemma-4-31B and Qwen-3.6-27B.72% similarUnverifiedAmong 8 locally run large models tested on a Raspberry Pi 5, only 3 genuinely passed the tests for speed and task completion.67% similarUnverifiedFor personal learning or local testing, it is recommended to use smaller models (such as 1B, 2.5B, or 3.5B).67% similarUnverifiedIn a test of 30 Three.js One-Shot programming problems, Qwen 3.8 passed 24 and Ornith 1.5 passed 15, both running under Q6 quantization.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1018319API
curl https://kongchang.com/api/v1/knowledge/claims/1018319MCP
get_claim(id=1018319)