Unverified50% confidenceBenchmarkExact time
When 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.
1
Sources
50%
Confidence
Long-term
Relevance
10/21/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIn testing, the 3-bit quantized version outputs at 53 tokens per second.68% similarUnverifiedABACUS programs achieve 99.67% macro-average accuracy on the three BIG-Bench Hard tasks.68% similarUnverifiedWhen DINOv3 ViT-H+/16 is pruned to 50% sparsity, removing 427 million parameters, ImageNet-1k linear probe accuracy drops by only 0.8%, without weight correction or retraining.67% similarUnverifiedIn a model comparison test, qwen2.5:3b correctly understood pace, produced 0 hallucinated place names, had a length error of 0.3%, peak memory of 259 MB, and took 106 seconds.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1079143API
curl https://kongchang.com/api/v1/knowledge/claims/1079143MCP
get_claim(id=1079143)