FLUX.2 [max]
Black Forest Labs' top FLUX.2 tier for image generation and editing, released in December 2025 with web-search grounding and support for up to 8 reference images. It is still widely used but now sits in the lower half of the LMArena text-to-image board, and Black Forest Labs has since launched FLUX 3 Image.
Black Forest LabsImage modelReleased December 2025Data checked October 18, 2026
This model is not in the current people's rankings: it is either new and still collecting votes, or ranked below the top 12. See the AI leaderboard for the models people rate highest.
Strengths and weaknesses
- Very large LMArena sample (over 123,000 votes), so its score is stable
- Priced from $0.07 per megapixel
- Supports up to 8 reference images and web-search grounding, according to Black Forest Labs
- 29th of 82 entries on LMArena text-to-image, far behind the 2026 models
- Superseded by FLUX 3 Image (October 1, 2026), which is not yet on LMArena
Best for
- Image editing with several reference images
- Creative tools that already integrate FLUX
Every score we have
Each bar compares this model with the best result any model on this page has on the same test.
- LMArena text to image1,162.1Arena score 1162.1 (95% CI 1158.6 to 1165.6); 123,203 votes; entry "flux-2-max"; position 29 of 82 on the full board
- LMArena image editing1,261.7Arena score 1261.7 (95% CI 1258.5 to 1264.8); 375,861 votes; entry "flux-2-max"; position 34 of 59 on the full board
- Artificial Analysis image arena1,020.2Elo 1020.2 (95% CI 1010.2 to 1030.2); 10,831 appearances; position 33 of 104 on the Artificial Analysis text-to-image arena
- Price per 1,000 images (estimate)$70$70.00 per 1,000 images (Artificial Analysis estimate)
Compare with
- GPT-Image-2.5 SunburstOpenAI's most capable image generation and editing model, released as a September 8, 2026 snapshot alongside the faster GPT-Image-2.5 Flare.
- Grok Imagine Image 2.0SpaceXSI's (formerly xAI) second-generation Grok Imagine image model for generating and editing images from text or image prompts.
- MAI-Image-2.6Microsoft AI's image model, launched on August 10, 2026 and offered in public preview on Microsoft Foundry.
- Nano Banana 2.1Google's latest Nano Banana image model (Gemini API code gemini-nano-banana-2.1), released on October 6, 2026 as an update to Nano Banana 2 with better quality, prompt adherence and text rendering.