Unverified50% confidenceFactExact time
In the scheme of running Qwen 3.5 on a 32-bit RISC CPU, math accuracy improved from 55% to 97.5%.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
11/1/2026
First Seen
Valid until: 11/15/2026
Sources
Related Entities
Related Claims
UnverifiedThe Top3 configuration achieved an accuracy of 97.148%, a weighted F1 of 97.055%, and an MCC of 0.9675, comprehensively outperforming the Full21 configuration using all 21 metrics (accuracy 95.999%, weighted F1 95.521%, MCC 0.9549).72% similarUnverifiedEfficientNet 从 B0 到 B7，模型参数从 5.3M 增长到 66M，Top-1 精度从 77.1% 提升到 84.3%70% similarUnverifiedABACUS programs achieve 99.67% macro-average accuracy on the three BIG-Bench Hard tasks.69% similarUnverifiedWhen a 3B small verifier is introduced, ProVe reaches an average 2.7x throughput, but its average accuracy across six tasks is 2.6 percentage points lower than AR.68% similarUnverifiedNVFP4量化方案相比BF16基线实现了1.5倍的推理加速，同时在top-1准确率上保留了92%到97%的水平68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1124698API
curl https://kongchang.com/api/v1/knowledge/claims/1124698MCP
get_claim(id=1124698)