Unverified50% confidenceBenchmarkExact time
Among all 16 configurations across 4 tasks × 4 models, not a single one passed the qualification threshold.
1
Sources
50%
Confidence
Long-term
Relevance
10/2/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedUltra multi-agent mode defaults to 4 agents in parallel and can be scaled up to a maximum of 16.64% similarUnverifiedRegardless of the encoding scheme used, 4-bit precision can only distinguish 16 different numerical levels.64% 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.63% 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.62% similarUnverified九个Checkpoint由四个目标模型（Qwen3的4B、8B、14B及Gemma 4的12B）乘以三种算法组成60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/966714API
curl https://kongchang.com/api/v1/knowledge/claims/966714MCP
get_claim(id=966714)