Unverified50% confidenceBenchmarkExact time
On 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.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/13/2026
First Seen
Valid until: 1/11/2027
Sources
Related Entities
Related Claims
UnverifiedThe fine-tuned Qwen3.5-4B model improved accuracy on BU Bench V1 from 15% to 53%.80% similarUnverifiedOn agentic coding benchmarks such as SWE Bench Pro, Qwen 3.8 reportedly surpasses Opus 4.6 Max on some tasks.74% similarVerifiedQwen3.5's parameter activation rate is 4.3%, while DeepSeek V3's 671B model has an activation rate of 5.5%.73% similarUnverifiedExperience internalization fine-tuning improved Qwen3-8B-27B's one-shot score from 37.07 to 48.22, while reducing generated tokens from 6.41 million to 570,000 (an 11-fold reduction).72% similarVerifiedGGUF量化格式（如Q4_K_M）通过将权重精度从32位浮点压缩到4位整数，通常只带来约1-5%的性能损失70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1013360API
curl https://kongchang.com/api/v1/knowledge/claims/1013360MCP
get_claim(id=1013360)