Run Detail
completedqwen3.8-max-0902Recorded 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
Batched — not timed
Total Tokens
75,500
Input Tokens
717
Output Tokens
74,783
Reasoning Tokens
73,431
Reasoning Effort
default
Est. Cost
$0.2588
Started
11/9/2026, 3:12:59 PM
OR Provider
Alibaba
Finish Reason
stop
Generation ID
gen-batch-1794237178-0251668f85a2e1d25525
Turns (1)
Turn #1
717 in74,783 out73,431 reasoning75,500 total
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 koi pond at dusk: three koi cruise in slow arcs beneath notched lily pads, rings spreading where their tails flick the surface, while a drifting patch of light dapples the water and a single pink bud glows on the far pad.
The file
<!doctype html><body style=margin:0><canvas id=c style=display:block><script>
x=c.getContext('2d'),W=c.width=innerWidth,H=c.height=innerHeight,t=0,R=[],P=[[.16,.24,86],[.84,.18,100],[.74,.82,64],[.52,.55,40]].map(p=>({x:p[0]*W,y:p[1]*H,r:p[2],h:p[0]*7})),F=[['#fff','#f73'],['#f73','#fff'],['#fc3','#321']].map((f,i)=>({b:f[0],m:f[1],a:i*2.1,p:i*2.6,x:W*(.3+.2*i),y:H*(.35+.15*i),tr:[]}));function D(f,o,C){M=[];for(i=0;i<24;i++){p=f.tr[i*2]||[f.x,f.y],q=f.tr[i*2+4]||p,u=p[0]-q[0],v=p[1]-q[1],l=Math.hypot(u,v)||1,e=Math.sin(t*.11-i*.5)*i/4,M.push([p[0]-v/l*e+o[0],p[1]+u/l*e+o[1]])}x.lineCap='round';for(i=0;i<23;i++){x.strokeStyle=C||i>2&&i<7||i>11&&i<16?f.m:f.b,x.lineWidth=2.8*(i<4?3+i*1.4:8.6-i*.38+(i>20?(i-20)*1.6:0)),x.beginPath(),x.moveTo(M[i][0],M[i][1]),x.lineTo(M[i+1][0],M[i+1][1]),x.stroke()}}function G(){t++;for(f of F){f.a+=.03*Math.sin(t*.011+f.p),u=f.x/W-.5,v=f.y/H-.5;if(u*u+v*v>.16)T=Math.atan2(-v,-u),f.a+=Math.sin(T-f.a)*.14;f.x+=Math.cos(f.a)*2.1,f.y+=Math.sin(f.a)*2.1,f.tr.unshift([f.x,f.y]);if(f.tr.length>60)f.tr.pop()}x.fillStyle='#032',x.fillRect(0,0,W,H),gx=W*(.5+.38*Math.sin(t*.0013)),gy=H*(.5+.38*Math.cos(t*.001)),g=x.createRadialGradient(gx,gy,0,gx,gy,(W+H)*.3),g.addColorStop(0,'rgba(110,230,190,.07)'),g.addColorStop(1,'rgba(0,0,0,0)'),x.fillStyle=g,x.fillRect(0,0,W,H);for(f of F)D(f,[9,15],'rgba(2,16,12,.4)'),D(f,[0,0],0);if(Math.random()<.03&&(p=F[Math.random()*3|0].tr[40]))R.push([p[0],p[1],2]);for(i=R.length;i--;){r=R[i],r[2]+=1.3,a=1-r[2]/80;if(a<=0){R.splice(i,1);continue}x.strokeStyle='rgba(180,235,215,'+a*.4+')',x.beginPath(),x.arc(r[0],r[1],r[2],0,7),x.stroke()}for(p of P){a0=p.h+.06*Math.sin(t*.012+p.h),x.fillStyle='#054',x.beginPath(),x.moveTo(p.x,p.y),x.arc(p.x,p.y,p.r,a0,a0+5.6),x.closePath(),x.fill()}q=P[0],x.fillStyle='#e9a',x.beginPath(),x.arc(q.x,q.y,8,0,7),x.fill(),g=x.createRadialGradient(W/2,H/2,W*.2,W/2,H/2,(W+H)*.55),g.addColorStop(0,'rgba(0,0,0,0)'),g.addColorStop(1,'rgba(1,10,8,.55)'),x.fillStyle=g,x.fillRect(0,0,W,H),requestAnimationFrame(G)}G()
</script>
The ledger
- Bytes: 2032
- How you counted: UTF-8 length of the exact file above (pure ASCII, so one byte per character), summed segment-by-segment over the serialized text, header and newlines included.
- Last thing cut: a six-petal open lotus and per-fish eyes; the bud is the survivor. The bloom would have given the corner pad a true focal flower, the eyes a fleck of life at the nose — together about 350 bytes I didn't have.
The technique
Each koi is nothing but a position history. The head wanders on layered sines with a soft elliptical steer back from the margins, and the body is the trail: 24 sampled points rendered as round-capped strokes whose widths taper from nose to peduncle and flare into the tail, with the koi's saddle patches falling out of two strokeStyle swaps mid-spine. One ~400-byte draw function — called once offset in dark translucent green, once in place — yields body, pattern, swimming undulation and pond-floor shadow with no polygons, no skeleton and no keyframes. Everything else (rings, pads, drifting light, vignette) could then be bought cheaply, because the subject itself cost one loop.
Attachments
qwen/qwen3.8-max-0902 — page