Unverified50% confidenceBenchmarkExact time
Pruning-based weakening raises the accuracy of Qwen3.5-4B on LiveCodeBench v6 from 39.1% to 56.7%.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/30/2026
First Seen
Valid until: 1/28/2027
Sources
Related Entities
Related Claims
UnverifiedPruning-based weakening raises the accuracy of Qwen3.5-4B on HMMT 2025 from 57.7% to 70.5%.79% similarUnverifiedWhen run on Qwen3.6-35B-A3B with a 50% expert pruning ratio, SlimWise increases decoding throughput by up to 1.81x with minimal accuracy loss.79% similarUnverifiedOn the Qwen3-VL-4B model, fine-tuning with procedurally generated data raises its accuracy on SpaceCast-Bench from 34.0% to 65.7%, and achieves a macro-average gain across six out-of-domain benchmarks.76% similarUnverifiedThe fine-tuned Qwen3.5-4B model improved accuracy on BU Bench V1 from 15% to 53%.76% similarUnverifiedAccording to the SWE-Bench Verified benchmark, Qwen 2.5 Coder 32B achieves a coding ability score of 61.773% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1114234API
curl https://kongchang.com/api/v1/knowledge/claims/1114234MCP
get_claim(id=1114234)