Unverified50% confidenceFactExact time
Qwen improved by 40.2 percentage points on MATH500, while Gemma improved by less than 1 percentage point, a difference of about 45 times.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
11/4/2026
First Seen
Valid until: 2/2/2027
Sources
Related Entities
Related Claims
UnverifiedQwen 3.8 is slower than 3.6, with prefill and inference speeds dropping by approximately 40% and 20% respectively.72% similarUnverifiedIn the experiment, Astra modified the weights of the small Qwen model, raising the MATH500 score from 7.9% to 48.1%, while the share of answers hitting the trial-run limit fell from 93% to 33%.66% similarUnverifiedOn overall intelligence, the highest among domestic models is 45 points for GLM and Qwen, an 8-point gap from the 53 points of GPT and Claude, a relative difference of about 15%.62% similarUnverifiedUnder Q2K quantization, average generation speed is 13.9 tokens per second for short texts, 10.5 for long texts, and peaks at approximately 18.62% similarUnverifiedBrandeis reports that the optimized branch can be up to 5.7 times faster than the main branch, and about 50 times faster overall relative to tokenizers version 0.23, but the two baselines differ, and the 50x includes improvements accumulated from earlier version iterations.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1135440API
curl https://kongchang.com/api/v1/knowledge/claims/1135440MCP
get_claim(id=1135440)