Decision support
FLUX.2 [dev] vs Qwen-Image-Edit
Compare canonical objects directly. The useful dimensions change with the object type, so model and hardware comparisons stay separate.
Black Forest Labs
Qwen
Benchmark results
Head to head on 1 benchmark both models report
- FLUX.2 [dev]0leads
- Qwen-Image-Edit1lead
Arena Text to Image
Arena rating · Higher is better
- FLUX.2 [dev]1145Arena #40CI 1141 to 1149
- Qwen-Image-EditNot reported
Runs and sources
FLUX.2 [dev]- default114595% CI 1141 to 1149 · 75,695 votes
Qwen-Image-EditNot reported
Arena Image Edit
Arena rating · Higher is better
- FLUX.2 [dev]1224Arena #47CI 1220 to 1228
- Qwen-Image-EditBest1241+17 ahead · Arena #41CI 1238 to 1244
Runs and sources
FLUX.2 [dev]- default122495% CI 1220 to 1228 · 247,732 votes
Qwen-Image-Edit- default124195% CI 1238 to 1244 · 2,000,722 votes
Each model's best published result is shown; "Not reported" means no matched evaluation, not a score of zero. Arena and DeepSWE ranks are the leaderboards' own; other ranks are among catalogue models with a score. Results from different harnesses or settings are not directly comparable.
Arena ratings: Arena (lmarena-ai/leaderboard-dataset), licensed CC BY 4.0. Ratings come from pairwise human votes and are only comparable within one leaderboard; the interval is Arena's 95% confidence interval. Model names are matched to the Vertical Tabs catalog.
Model specifications
API pricing · USD per 1M tokens
Capabilities and modalities
Architecture and availability
A dash means the field is not reported. Provider-specific performance and pricing may differ.