Run Detail
completedclaude-fable-5Recorded 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
21,863
Input Tokens
884
Output Tokens
20,979
Reasoning Tokens
19,108
Reasoning Effort
medium
Est. Cost
$0.5289
Started
8/21/2026, 10:30:13 PM
OR Provider
Anthropic
Finish Reason
stop
Generation ID
gen-batch-1787351414-e1f06a9aa823be12c30c
Turns (1)
Turn #1
884 in20,979 out19,108 reasoning21,863 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 murmuration at dusk: ninety starlings wheeling over a darkening sea, drifting clouds, a low sun laying a shivering reflection on the water, stars coming out overhead.
The file
<!doctype html><meta charset=utf-8><title>Vesper</title><body style=margin:0><canvas id=c style=display:block></canvas><script>M=Math,R=M.random,X=c.getContext('2d');onresize=Z=_=>{W=c.width=innerWidth;H=c.height=innerHeight};Z();B=[];for(i=0;i<90;i++)B[i]={x:R()*W,y:R()*H/2,u:1,v:0,p:R()*9};t=0;setInterval(_=>{t+=.02;h=H*.72;sx=W/2;sy=h-H*.05;g=X.createLinearGradient(0,0,0,h);g.addColorStop(0,'#150a2e');g.addColorStop(.6,'#84364d');g.addColorStop(1,'#ff9a3c');X.fillStyle=g;X.fillRect(0,0,W,h);g=X.createRadialGradient(sx,sy,0,sx,sy,H/3);g.addColorStop(0,'rgba(255,220,150,.7)');g.addColorStop(1,'rgba(255,150,60,0)');X.fillStyle=g;X.fillRect(0,0,W,h);X.fillStyle='#ffe9b0';X.beginPath();X.arc(sx,sy,H/22,0,7);X.fill();for(i=0;i<45;i++){X.fillStyle='rgba(255,255,255,'+.35*(.5+.5*M.sin(t*2+i*3))*(i%7)/7+')';X.fillRect(i*i*37%W,i*i*53%(h/2),1.5,1.5)}for(i=0;i<8;i++){X.fillStyle='rgba(55,20,45,.5)';X.beginPath();X.ellipse(i*i*97%W+50*M.sin(t/9+i),h*(.25+i*.08),80+i*22,3+i,0,0,7);X.fill()}g=X.createLinearGradient(0,h,0,H);g.addColorStop(0,'#5b2438');g.addColorStop(1,'#0d0518');X.fillStyle=g;X.fillRect(0,h,W,H);for(i=0;i<70;i++){y=h+2+i*i%97/97*(H-h);d=(y-h)/(H-h);w=(6+34*d)*(.6+.4*M.sin(t*4+i*5));X.fillStyle='rgba(255,180,90,'+.5*(1-d)*(.5+.5*M.sin(t*3+i*7))+')';X.fillRect(sx-w/2+M.sin(i*i)*45*d,y,w,1.5)}tx=W*(.5+.32*M.sin(t*.4)+.1*M.sin(t*1.3));ty=H*(.3+.14*M.sin(t*.55)+.06*M.sin(t*1.1));X.strokeStyle='#12081c';X.lineWidth=1.3;X.beginPath();for(b of B){for(o of B){dx=b.x-o.x;dy=b.y-o.y;d=dx*dx+dy*dy;if(d&&d<500){b.u+=dx/d*4;b.v+=dy/d*4}}b.u+=(tx-b.x)/999+R()*.3-.15;b.v+=(ty-b.y)/999+R()*.3-.15;if(b.y>h-40)b.v-=.3;s=M.hypot(b.u,b.v);if(s>2.4){b.u*=2.4/s;b.v*=2.4/s}b.x+=b.u;b.y+=b.v;f=M.sin(t*24+b.p*3)*4;s=4+2*M.sin(b.p);X.moveTo(b.x-s,b.y+f);X.lineTo(b.x,b.y);X.lineTo(b.x+s,b.y+f)}X.stroke()},30)</script>
The ledger
- Bytes: 1827
- How you counted: Single line, pure ASCII (1 byte = 1 char), no trailing newline; summed per-statement and cross-checked section totals.
- Last thing cut: Per-bird heading — rotating each V to face its velocity vector via
atan2and a small transform. It would have made the wheeling turns read even better, but the flap plus flock motion sells the silhouette and the rotation code cost ~90 bytes I preferred to spend on clouds and the sun's reflection.
The technique
The structural decision was to give the scene no stored state except the birds. Everything else — star positions, star twinkle phases, cloud placement, every glint of the sun's reflection on the water — is derived fresh each frame from the loop index by cheap integer hashing (i*i%prime for position, sin(t*k+i*k') for shimmer). That means the sky, sea and reflection cost zero bytes of data and zero setup code, are automatically stable frame-to-frame yet alive, and survive window resizes for free. The entire remaining budget could then go where a subject actually lives: a real O(n²) boids loop (separation + a slowly wandering attractor built from incommensurate sines, so the flock genuinely never repeats), drawn as one shared stroked path so ninety flapping birds cost a single beginPath/stroke pair.
Attachments
anthropic/claude-fable-5 — page