Unverified50% confidenceBenchmarkExact time
On the report's selected Top-5 single-image targets, FLUX.2 [dev]'s Overall score rose from 1.083 to 3.517, and Qwen-Image-Edit-2511 achieved a 13.2% improvement.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
11/2/2026
First Seen
Valid until: 11/16/2026
Sources
Related Entities
Related Claims
UnverifiedUnder the condition of matched per-step generation budgets, FOCUS at the Qwen3.5-9B scale improves by 7.2 percentage points over the strongest baseline (the higher of GRPO/VinePPO) on the BrowseComp-Plus benchmark, reaching 55.4 versus 48.2.68% similarUnverifiedOn Qwen-Image-Edit, Rubric-CEPR improved ImgEdit from 4.36 to 4.60, a gain of +5.5%.67% similarUnverifiedOn the Qwen3.5-4B and 9B models, using only GGA allocation without any other changes improved the scores on seven evaluations by 19.48 and 29.84 percentage points, respectively, compared with STEPQuant@4.67% similarUnverifiedThe composite score of reports selected by the full composite objective rose to 0.4122.67% similarPartially VerifiedV4.1 Flash 1017's score on Terminal-Bench 4.0 rose from 31.2% to 42.3%, a relative improvement of 35% in five weeks.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1125248API
curl https://kongchang.com/api/v1/knowledge/claims/1125248MCP
get_claim(id=1125248)