Unverified50% confidenceBenchmarkExact time
VASPO improves average accuracy by 2.59 percentage points over PPO on Qwen3-4B and by 1.81 percentage points on OLMo3-7B.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/15/2026
First Seen
Valid until: 1/13/2027
Sources
Related Entities
Related Claims
UnverifiedThe fine-tuned Qwen3.5-4B model improved accuracy on BU Bench V1 from 15% to 53%.71% similarUnverifiedOn the Qwen3-VL series of models (from 2B to 30B-A3B) and on InternVL3.5-8B, SPLIT-RL improves average accuracy by 1.4 to 6.1 percentage points compared to standard GRPO.69% similarUnverifiedAt a throughput of 259k, Qwen3.5 achieves approximately a 19× speed improvement, with hybrid attention contributing approximately 5×, MoE sparsification approximately 2×, and Multi-Token Prediction approximately 1.5×.66% similarUnverifiedThe Q3_K_M quantized model's accuracy improved from 52% to 66%, representing the largest improvement.66% similarUnverifiedPiPMRE achieves an average improvement of 4.4 percentage points in precision over the previous state-of-the-art methods on two public datasets.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1032841API
curl https://kongchang.com/api/v1/knowledge/claims/1032841MCP
get_claim(id=1032841)