Unverified50% confidenceBenchmarkExact time
Zero-shot Qwen2.5-VL-3B-Instruct achieved a full-invoice exact rate of 5.3% and an auto-approval rate of 8.1% on the test set; the OCR + rules baseline achieved a full-invoice exact rate of 37.8% and an auto-approval rate of 55.0%.
1
Sources
50%
Confidence
Long-term
Relevance
10/15/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedTesting with the Qwen model yielded consistent conclusions, with the token approach achieving 67.0% accuracy versus 64.8% for real data.74% similarUnverifiedIn a speculative decoding test using Qwen2.5 0.5B as the draft model proposing 4 tokens at a time, the overall draft acceptance rate was 32.9% for serial processing and 37.1% for concurrent processing.72% similarUnverifiedQwen Next scored only 6/108 (5.56%) in testing due to format reliability issues (17 invalid_json responses, with only 6 entries scorable) rather than insufficient comprehension.70% similarUnverifiedOn "continuation of previous operation" type utterances, Qwen3.6-35B-A3B achieved an accuracy of 86.3%, while the 4B and 8B models achieved only 70.4%.68% similarUnverifiedThe random-position null baseline for Qwen3-4B was only 11.3%, and the upper bound for directly patching lower-level prompt facts was 83%.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1036980API
curl https://kongchang.com/api/v1/knowledge/claims/1036980MCP
get_claim(id=1036980)