DeepSeek V4.1 Flash vs Gemini 3.8 Flash at 3D geometry
test: six self-contained three.js stereometry scenes — a (3,8) torus knot, a Klein bottle, a great stellated dodecahedron, a hyperboloid ruled by 120 straight rods, a level-3 Menger sponge, a thick Möbius strip. one shot each, no libraries beyond three.js, every surface painted with a live iridescent rainbow that has to crawl across the geometry.
cost:
Gemini 3.8 Flash — $0.11
DeepSeek V4.1 Flash — $0.27
• gemini delivers all six figures for 2.4× less — 21k output tokens against deepseek's 168k
• gemini is 5× faster — every scene under 25 seconds, deepseek took up to 3 minutes on the Möbius strip
• deepseek wins the torus knot: its rope is vivid and glossy, while gemini rendered the same knot nearly black
• neither model can build a real Klein bottle. both hand back a twisted tube and call it done
try both on aimlapi[.]com
GPT Images 2.5 beats Nano Banana Pro on detail and color
the test: five one-shot image prompts, identical text for both models — a crab scoring through a ring of fire at sea, a cat devouring galaxies, a girl with a laser cannon vs giant octopuses, a crocodile fighting a hot dog army in a rainbow valley, a giant banana with laser eyes leveling a metropolis. one generation each, no retries, no cherry-picking.
interesting:
• gpt packs every frame with detail — individual droplets on the crab's shell, hundreds of hot dog soldiers in one shot, debris flying off every collapsing tower
• gpt's colors just hit harder — deeper saturation, hotter fire, real neon in the laser beams
GPT Astra just cooked Claude Fable 5.1 — for a lower price!
OpenAI just rolled out GPT‑6 Astra — we put it against Anthropic's Fable 5.1
Both models got the same four briefs: Earth colliding with Mars, a tall ship sucked into a giant whirlpool, Godzilla leveling downtown, a mega-tsunami swallowing a city. One self-contained HTML file per scene, one shot, no edits.
GPT Astra: 25,159 tokens, $1.67
Claude Fable 5.1: 37,767 tokens, $2.51
both models live on aimlapi[.]com — 1000+ models, one key.
Gemini Flash 3.8 beats Opus 5 at at 15× lower price
the test: four self-contained three.js physics scenes — a balloon popped by a needle, a ball dropping into water, a bomb with a mushroom cloud, a live atom model. 5 seconds each, real gravity, real impact.
cost:
Gemini 3.8 Flash — $0.12
Claude Opus 5 — $1.86
what we saw:
• gemini passes the same physics checklist for 15× less — the ball sinks and bobs, ripples spread, the mushroom towers over the scene
• gemini is 4× faster — every scene generated in under 70 seconds. opus took up to 5 minutes
try Gemini 3.8 Flash on aimlapi[.]com
@aimlapi@Zai_org tbh, it did a good job, and I’d say it’s a draw in this video.
yes, GPT created a toy lizard, but it looks more like Godzilla to me :)))
GLM-5.3 vs GLM-5.2: build your own landing page
@Zai_org says their new model is built to code — so we ran a head-to-head. Both models got the exact same brief: build a landing page for yourself, one self-contained HTML file each.
The typing terminal, the springy benchmark charts, the working tabs and FAQ, the 3D backgrounds — all their own code. No frameworks, no templates.
GLM-5.3: 161,971 tokens, $0.80.
GLM-5.2: 197,853 tokens, $0.98.