Unverified50% confidenceBenchmarkExact time
Qwen3.8-27B scored 91.1 on OmniDocBench v1.5, the strongest document parsing score among the generative models in this evaluation.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/13/2026
First Seen
Valid until: 1/11/2027
Sources
Related Entities
Related Claims
UnverifiedIn the request type judgment task, the ordinary qwen3:8b and qwen3.5:4b models achieved an accuracy of about 82%.73% similarUnverifiedIn the tool-calling benchmark BFCL, Qwen3 scored 83%.73% similarUnverifiedQwen2.5-3B-Instruct achieved an overall score of 0.90 on EvidenceFlip, with an action accuracy of 0.90, conflict detection of 1.00, and pressure resistance of 1.00.71% similarUnverifiedOn Qwen-3.5-4B-Instruct, 75.6% of validity scores judged that the generated results at both poles of the principal axes accurately corresponded to their labels, with an annotator adjacent-agreement rate as high as 90.9%.71% similarUnverifiedThe fine-tuned Qwen3.5-4B model improved accuracy on BU Bench V1 from 15% to 53%.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1013927API
curl https://kongchang.com/api/v1/knowledge/claims/1013927MCP
get_claim(id=1013927)