Unverified50% confidenceBenchmarkExact time
On WebArena-Infinity, Qwen3.5-4B improved from solving 31 out of 119 tasks to 50.
1
Sources
50%
Confidence
Long-term
Relevance
10/5/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedOn OpenApps, Qwen3.5-4B improved from 3 out of 100 tasks to 15.78% similarUnverifiedOfficial benchmark data shows that the new version of Qwen3 27B agent coding improved from 13.3 to 42.2, software engineering tasks improved from 49.3 to 79, and frontier agent tasks improved from 10.6 to 20.76% similarUnverifiedA developer used the Qwen3.8-27B model to complete the Wikipedia speedrun game within 6 clicks.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/975839API
curl https://kongchang.com/api/v1/knowledge/claims/975839MCP
get_claim(id=975839)