Fast distilled version of Black Forest Labs' FLUX.2 [dev] optimized for speed and cost efficiency.
Settled by community votes across 4 shared challenges, with an AI judge weighing in on each.
FLUX.2 [dev] Flash
26.8
arena score
#5 of 44 in Text-to-Image
Skill signature
Not enough comparable category data
The chart appears once both models have ratings across at least three shared arena categories.
Wan 2.6
23.4
arena score
#23 of 44 in Text-to-Image
Best Image-to-Video right now
Vote tally
Where the votes landed
FLUX.2 [dev] Flash
100.0%
win rate
Ties
0.0%
Wan 2.6
0.0%
win rate
100.0%
0.0% ties
0.0%
Shared challenges
4
Challenge by challenge
The strongest take from each model on every shared challenge, with the AI judge's read.
Chalkboard Menu
Text-to-Image“Handwritten-style chalkboard menu in a cozy café, all text rendered in the exact same realistic chalk handwriting style with natural variations in letter size, slight slant, and chalk texture — no printed or digital fonts anywhere on the board. Title at the top in elegant cursive chalk handwriting: ‘TODAY’S SPECIALS – APRIL 30, 2026’. Below it, three menu items also in the same handwritten chalk style: ‘Truffle Mushroom Risotto – $24’, ‘Grilled Octopus with Lemon & Herbs – $28’, ‘Brown Butter Chocolate Chip Cookies – $9’. At the very bottom, smaller text in the identical handwritten chalk style (slightly smaller but still clearly legible with the same handwriting characteristics): ‘All items made fresh daily • Ask about our gluten-free options’. Warm ambient café lighting, visible chalk dust and smudges, realistic handwriting imperfections, no clean printed text anywhere.”
FLUX.2 [dev] Flash
Wan 2.6
AI Judge Analysis
FLUX.2 [dev] Flash
- + Excellent text rendering with clean, legible handwriting.
- + Captures the realistic texture of chalk including dust and smudges.
- + Almost perfect adherence to the long list of menu items.
- − Includes a stray dollar sign at the end of the cookie line.
- − The layout becomes slightly cramped at the bottom.
Wan 2.6
- + Natural, slanted handwriting style that feels very authentic to a café.
- + Great lighting and chalkboard frame composition.
- + Correctly interprets the three menu items without extra punctuation errors.
- − Repeats the word 'Chip' in the cookie item ('Chip Cookies').
- − The handwriting is slightly less uniform in quality compared to Model A.
Verdict: Both models performed exceptionally well on a difficult text-heavy prompt, capturing the chalk texture and specific dates/prices perfectly. FLUX.2 [dev] Flash has slightly cleaner lettering but included a stray dollar sign, while Wan 2.6 captured a more natural 'slanted' handwriting style but suffered from a minor word repetition error.
The Capybara Taxi Driver
Text-to-Image“Photorealistic scene inside a yellow New York taxi at night. A capybara is driving, wearing a yellow taxi driver cap and a dark jacket. It has a calm, professional expression and both front paws on the steering wheel. In the back seat sits a human businesswoman in a coat, looking at her phone with a completely normal, bored expression (as if this is just another normal ride). Through the windows you can see the streets of Manhattan at night with blurred lights. Realistic taxi interior, photorealistic, detailed fur and fabric, 35mm lens, night lighting with reflections, shallow depth of field.”
FLUX.2 [dev] Flash
Wan 2.6
AI Judge Analysis
FLUX.2 [dev] Flash
- + Excellent photorealism in textures, especially capybara fur and the jacket.
- + Perfect adherence to the 'bored expression' prompt for the passenger.
- + The passenger is correctly placed in the back seat as requested.
- − The perspective from outside the hood looking through the windshield makes the interior feel slightly less present.
- − Text on the car light is a bit garbled ('TAX').
Wan 2.6
- + Dynamic cinematic lighting and vibrant night-time city bokeh.
- + Detailed costume design with a more authentic-looking driver's cap.
- + Side-angle composition offers a better view of both the steering wheel interaction and the city.
- − The passenger appears to be in the middle of a two-door vehicle rather than the back seat of a standard sedan taxi.
- − The interior of the door/car lacks the 'clean professional' taxi look requested, appearing a bit worn or weathered.
Verdict: FLUX.2 [dev] Flash adhered better to the spatial requirements of the prompt by placing the passenger in the back seat and capturing the specific 'bored' expression perfectly. While Wan 2.6 has more vibrant colors and an impressive side profile, the passenger placement and vehicle interior felt less like a standard New York taxi and more like a cramped courier vehicle.
Isometric Miniature Diorama Scenes
Text-to-Image“Create a clear, 45° top-down isometric miniature 3D cartoon scene of Japan's signature dish: sushi, with soft refined textures, realistic PBR materials, gentle lighting, on a small raised diorama base with minimal garnish and plate. Solid light blue background. At top-center: 'JAPAN' in large bold text, 'SUSHI' below it, small flag icon. Perfectly centered, ultra-clean, high-clarity, square format.”
FLUX.2 [dev] Flash
Wan 2.6
AI Judge Analysis
FLUX.2 [dev] Flash
- + Excellent text rendering with clean, bold typography.
- + Higher texture detail on the fish and wasabi, giving it a high-quality PBR look.
- + Strong adherence to the 45-degree isometric perspective.
- − The sushi pieces are somewhat merged together in an anatomically strange way.
- − The flag icon is placed to the right of the word 'SUSHI' instead of following the vertical hierarchy implied by the prompt.
Wan 2.6
- + Perfectly follows the diorama base requirement with a clear tiered platform layout.
- + Distinct, well-organized sushi pieces (salmon, tuna, shrimp).
- + Clean composition with a nice balance of colors.
- − Text is slightly less crisp than Model A.
- − The flag icon is placed to the left of 'SUSHI' rather than below the text block in a secondary position.
- − The textures appear a bit more 'plastic' and less like the requested PBR materials.
Verdict: Both models followed the prompt well, but FLUX.2 [dev] Flash stands out for its superior text rendering and more realistic material textures. Wan 2.6 provided a better diorama composition with more variety in the sushi types, but FLUX.2's overall clarity and professional finish make it the stronger image.
Apollo 11: Journey to Tranquility
Text-to-Image“Create a clean, modern vector infographic poster about the Apollo 11 mission. NASA-inspired palette (navy, white, muted red, light gray). Flat-vector style, crisp lines, consistent iconography, subtle gradients only. Steps (stop at landing): 1. Launch (Saturn Vicon) 2. Earth Orbit (Earth + orbit ring icon) 3. Translunar (trajectory arc icon) 4. Lunar Orbit (Moon + orbit ring icon) 5. Descent (lunar module descending icon) 6. Landing (lunar module on the surface icon) Small supporting elements (minimal text): • Crew strip: three silhouette icons with only last names: Armstrong, Aldrin, Collins. • Landing site marker: Moon pin labeled "Tranquility" only. Layout constraints: generous margins, large readable labels, clean background with subtle stars. Vector-only, print-poster look, high resolution.”
FLUX.2 [dev] Flash
Wan 2.6
100% wins
0% ties
0% wins
AI Judge Analysis
FLUX.2 [dev] Flash
- + Successfully included all requested infographic stages from Launch to Landing.
- + Followed the NASA-inspired color palette perfectly.
- + Contains readable and relevant text including the astronaut names and mission steps.
- − Some text elements contain gibberish or spelling errors like 'Sataurri Iccòn'.
- − The layout is a bit cluttered with redundant labels for 'Descent' and 'Landing'.
Wan 2.6
- + Clean, minimalist aesthetic with crisp typography.
- + Correctly identified the primary astronauts for the mission.
- − Failed to include any of the six requested infographic steps/icons.
- − The composition is mostly empty space, lacking the 'infographic' requirement entirely.
Verdict: FLUX.2 [dev] Flash followed the complex prompt instructions by creating a multi-stage infographic with icons and labels for each requested step of the mission. While it has some minor text artifacts, it is a functional poster, whereas Wan 2.6 ignored the majority of the prompt's content requirements, providing only a title and astronaut names.
Next steps
Explore each model
Alibaba's multimodal generation model from the Wan AI suite, supporting text-to-video, image-to-video, reference-to-video with audio, and text-to-image, in both Chinese and English