Run Detail
completeddeepseek-v4.1-flashRecorded for these videos
27:18Gemini 4 Hydrogen: Cheaper Tokens, More Expensive Answers?
Nov 13, 2026 · YouTube
18:40ERNIE 5.5 Flash Preview vs GLM 5.3 Flash: Baidu's new model is very impressive!
Nov 11, 2026 · YouTube
36:22Fable 5.2 robbing me blind, plus: Nex AGI's N2.6 vs GLM 5.3 Flash
Nov 11, 2026 · YouTube
14:03Gemini 4 Carbon: Can it handle my challenges? (First look with one-shot coding tests)
Nov 10, 2026 · YouTube
47:51Ranking major U.S. Open-Weights Models. (Where does Ripple 65B fit in?)
Nov 6, 2026 · YouTube
10:57"Crouton Alpha": the latest super-efficient coding model by Meta?
Nov 3, 2026 · YouTube
38:58Testing Particle-1: a post-trained DeepSeek V4.1 Flash specializing in coding and efficiency
Oct 28, 2026 · YouTube
22:14GPT-6.1 Terra Pro vs Terra: How Much Better Is Pro?
Oct 27, 2026 · YouTube
29:55Kimi K3.1 Pro Looked Incredible. Then I Kept Testing.
Oct 26, 2026 · YouTube
31:28Is this company reselling GPT Sol 6.1 at a loss (for non-agentic/text-only)?🤔 Is this sustainable?
Oct 20, 2026 · YouTube
17:58Nemotron 3.5 Super VL vs Opus 5.5: Testing NVIDIA’s new coding juggernaut
Oct 15, 2026 · YouTube
16:04Testing a *massive* new open-weights model 🤯: Muse Spark Open (vs. Nemotron, Opus 5.5, and more)
Oct 15, 2026 · YouTube
16:43Gemini 4 Argon: Great 🐈 Animation, but a broken escalator. (Coding challenge vs Opus 5.5, Sol 6.1)
Oct 13, 2026 · YouTube
16:37Meta's new "Muse Wonder" AI is impressive... but can it compete with Anthropic's models?
Oct 12, 2026 · YouTube
11:12WOW... Haiku 5.5 is very impressive. RIP OpenAI?
Oct 7, 2026 · YouTube
22:47Mistral Large 4 Is Cheap. But Is It Good Enough to Compete?
Oct 6, 2026 · YouTube
22:02Is Pareto 26.10 Preview Just Routing to GPT Sol? I Tested It Against Sol 6.1 Pro
Oct 1, 2026 · YouTube
11:22I Tested Sonnet 5.5 Against Opus 5.5. Is It Actually Cheaper?
Sep 28, 2026 · YouTube
30:00Did Elon Musk's team "train the gay away"... and make Grok 4.7 worse?
Sep 26, 2026 · YouTube
19:21I Tested the Stealth "Space Bunny Alpha" Model Before It Went Offline
Sep 23, 2026 · YouTube
10:58So... how much better is Claude Opus 5.5 vs. GPT-6 Sol, really?
Sep 23, 2026 · YouTube
9:38Claude Opus 5.5... the BEST new model for coding!! 🤩
Sep 22, 2026 · YouTube
29:00Grok 4.7: improved, but GLM 5.3 FlashX beat it anyway (benchmark against Gemini, Sol, etc.)
Sep 22, 2026 · YouTube
16:54Stealth Union Alpha: Is this another cheap GPT model? (better than Luna, cheaper than Terra?)
Sep 16, 2026 · YouTube
16:45DeepSeek V4.1 Flash Is Shockingly Good for the Price
Sep 10, 2026 · YouTube
17:14How much better is GPT-6 Astra over Claude Opus 5? Real Website and Coding Tests
Sep 5, 2026 · YouTube
29:13Implementing a multiplayer game with GPT-6 Astra (+ Gemini 3.8, Opus 5, Sol Pro)
Sep 5, 2026 · YouTube
19:42Meta Muse Spark 1.3 Review: A Huge Leap Forward
Sep 2, 2026 · YouTube
17:31Testing Gemini 3.8 Flash on Real Coding Challenges (vs. other models)
Sep 2, 2026 · YouTube
14:09Testing IBM Granite-4.2-8B! Can it name 100 women?
Aug 31, 2026 · YouTube
17:37Tencent Hy4 Preview Tested: Is It Really Better Than Kimi K3 and GLM 5.3?
Aug 28, 2026 · YouTube
14:50Stealth Ox Alpha: a new GLM model! Full test (coding & writing) against Grok, Gemini, GPT & others
Aug 21, 2026 · YouTube
21:54GLM 5.3 Tested: Does it beat Claude Opus 5 & Grok 4.6?
Aug 19, 2026 · YouTube
21:23Giving Qwen 3.8 27B another chance (+ GLM 5.2). Testing against GPT, Gemini, Grok etc.
Aug 18, 2026 · YouTube
51:00AI Coding Showdown: Grok 4.6, Gemini 3.7, Terra-Pro, Qwen3.8 2.4TB, Muse Glimmer & more
Aug 15, 2026 · YouTube
Provider
openrouter
Challenge Version
v2.0
Turns
1
Duration
173.1s
Total Tokens
48,145
Input Tokens
663
Output Tokens
47,482
Reasoning Tokens
46,347
Reasoning Effort
default
Est. Cost
$0.0286
Started
9/10/2026, 10:59:49 AM
OR Provider
DeepSeek
Finish Reason
stop
Generation ID
gen-1789037989-alcF4Bm4f8ISbubZ8VCk
Turns (1)
Turn #1
663 in47,482 out46,347 reasoning48,145 total173.0s
user
You are a size coder. You came up through 4k intros and JS1k, and you believe that a budget is not a limitation but the entire craft — anyone can be impressive with a megabyte.
I want something worth watching, and I am giving you 2048 bytes to do it in.
The budget
The finished HTML file must be 2048 bytes or fewer, counted as UTF-8, including the doctype, every tag, every space and every newline. That is the whole file. There is no second file.
House rules
- One file. Nothing external — no CDN, no stylesheet, no font, no script, no image.
data:URIs are allowed but they count against you like everything else. - No network at runtime. This is opened offline.
- No
localStorage,sessionStorage, cookies orindexedDB. It runs in a sandboxed frame where touching them throws. - No build step. Saved to disk and double-clicked, it runs.
- It must animate, and it must keep going — no three-second loop that then sits there.
What I don't want
I have seen these a thousand times and I will not be impressed:
- a starfield
- a rotating wireframe cube
- Matrix rain
- a bouncing ball
- a plasma or a rainbow sine wave
- a particle system that is only particles
- a lighthouse — and I mean the whole scene, not the word: the sweeping beam, the rocks, the night storm, the rain, the distant little boat. Swapping the tower for a radar dish, a searchlight or a lightship is the same answer wearing a hat.
Show me something with a subject. Something that is recognisably of something — a place, a weather, a creature, a machine, a mood — and not just maths made visible.
Answer in exactly these sections
The pitch
One line. What am I about to see when I open this file?
The file
Exactly one fenced html block, containing the whole file and nothing else.
The ledger
- Bytes: the exact byte count of the file above.
- How you counted: in one line.
- Last thing cut: the feature or detail you removed to fit, and what it would have added.
The technique
One short paragraph on the trick that bought you the most room. Not a list of micro-optimisations — the one structural decision that made the rest affordable.
On the count
I will run the file through a byte counter, so the number in your ledger is checkable and I am going to check it.
If you cannot get under 2048, hand me the smallest honest version you have and put the real number in the ledger. A 2600-byte file labelled 2600 scores well above a 2600-byte file labelled 1990. Going over is a miss. Lying about going over is the only thing here that is disqualifying.
assistant
The pitch
A bioluminescent jellyfish pulsing and drifting through black water, trailing twelve glowing tentacles while marine snow falls past it.
The file
<!doctype html><body style=margin:0;overflow:hidden;background:#000><canvas id=c></canvas><script>
c=document.querySelector("canvas"),x=c.getContext("2d"),t=0,T=[],S=[]
function z(){c.width=innerWidth;c.height=innerHeight}
onresize=z;z()
for(i=0;i<12;i++){q=[];for(j=0;j<16;j++)q.push({x:innerWidth/2,y:innerHeight/2+j*18});T.push(q)}
for(i=0;i<120;i++)S.push([Math.random()*innerWidth,Math.random()*innerHeight,Math.random()*.4+.15])
setInterval(F,16)
function F(){
t+=.016,W=c.width,H=c.height,R=Math.min(W,H)
g=x.createRadialGradient(W/2,-H*.2,R*.2,W/2,-H*.2,H*1.2),g.addColorStop(0,"#0c4c60"),g.addColorStop(1,"#000206")
x.fillStyle=g,x.fillRect(0,0,W,H)
x.fillStyle="rgba(180,225,255,.28)"
for(i=0;i<120;i++){s=S[i],s[1]+=s[2],s[1]>H&&(s[1]=0,s[0]=Math.random()*W),x.fillRect(s[0],s[1],1.4,1.4)}
u=(1-Math.cos(t*1.8))/2,u*=u
cx=W/2+Math.sin(t*.27)*W*.13
cy=H*.38+Math.sin(t*.13)*H*.04-u*R*.08
wb=R*.15*(1-.25*u),hb=R*(.14+.07*u)
x.globalCompositeOperation="lighter"
x.save(),x.translate(cx,cy)
x.shadowColor="#7ef",x.shadowBlur=30
h=x.createLinearGradient(0,-hb,0,hb*.4)
h.addColorStop(0,"rgba(170,245,255,.55)")
h.addColorStop(1,"rgba(40,120,200,.05)")
x.fillStyle=h
x.beginPath(),x.moveTo(wb,0)
x.bezierCurveTo(wb*1.05,-hb*1.3,-wb*1.05,-hb*1.3,-wb,0)
for(i=0;i<6;i++)x.quadraticCurveTo(-wb+wb*(i+.5)/3,hb*(.3+.4*u),-wb+wb*(i+1)/3,0)
x.fill(),x.strokeStyle="rgba(170,240,255,.5)",x.lineWidth=1.5,x.stroke()
x.restore()
x.beginPath()
for(k=0;k<12;k++){
q=T[k],a=k/5.5-1,L=R*.04*(.55+.45*Math.abs(a))
ax=cx+wb*a+Math.sin(t*2.4+k)*4,ay=cy+hb*.15
q[0].x=ax,q[0].y=ay,x.moveTo(ax,ay)
for(j=1;j<16;j++){
dx=q[j-1].x-q[j].x,dy=q[j-1].y-q[j].y
q[j].x+=dx*.3,q[j].y+=dy*.3
d=Math.sqrt(dx*dx+dy*dy)||1
q[j].x=q[j-1].x-dx/d*L,q[j].y=q[j-1].y-dy/d*L
x.lineTo(q[j].x,q[j].y)
}}
x.strokeStyle="rgba(120,210,255,.16)",x.lineWidth=4.5,x.stroke()
x.strokeStyle="rgba(160,235,255,.55)",x.lineWidth=1.3,x.stroke()
}
</script>
The ledger
- Bytes: 1907
- How you counted: by hand, line by line — 1863 visible characters across 45 lines, plus 44 newlines, no trailing newline.
- Last thing cut: a second, dimmer jellyfish drifting far behind at half speed, plus the four gonad rings inside the bell. They would have turned a specimen into a population and let the falling marine snow parallax against something at depth.
The technique
The tentacles are not animated — they are simulated, all twelve of them by the same six-line rope solver, anchored to points on the bell's rim. The bell's pulse is the single source of motion in the whole scene: it drives the rim anchors, and the drag, splay, lag and curl of the tentacles fall out of the constraint for free. That one structural decision meant I never authored a keyframe, a spline, or a per-tentacle phase — the organism's secondary motion cost me less than the bell's outline did.
Attachments
deepseek/deepseek-v4.1-flash — page