Run Detail
completedclaude-sonnet-5.5Recorded 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
28,454
Input Tokens
886
Output Tokens
27,568
Reasoning Tokens
25,811
Reasoning Effort
default
Est. Cost
$0.1387
Started
9/28/2026, 8:15:41 PM
OR Provider
Anthropic
Finish Reason
stop
Generation ID
gen-batch-1790626541-14ed9f3c113e0f0eb196
Turns (1)
Turn #1
886 in27,568 out25,811 reasoning28,454 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 steam train pulling lit passenger carriages through purple dusk hills under a clouded moon, with telegraph poles and sagging wires flicking past the windows and sparks streaming back from the chimney.
The file
<!DOCTYPE html><body style=margin:0;overflow:hidden;background:#000><canvas id=c width=320 height=180 style=width:100vw;height:100vh;object-fit:contain;image-rendering:pixelated><script>
x=c.getContext`2d`;R=(s,a,b,w,h)=>{x.fillStyle=s;x.fillRect(a,b,w,h)};
O=(s,a,b,r)=>{x.fillStyle=s;x.beginPath();x.arc(a,b,r,0,7);x.fill()};
F=t=>{with(Math){t/=1e3;
g=x.createLinearGradient(0,0,0,150);g.addColorStop(0,'#104');g.addColorStop(1,'#c65');
x.fillStyle=g;x.fillRect(0,0,320,180);
O('#fec2',240,36,24);O('#fec',240,36,11);
for(i=0;i<4;i++){X=380-(t*5+i*110)%440;Y=20+i*17%30;R('#3024',X,Y,70,3);R('#3024',X+15,Y-2,40,2)}
for(l=0;l<3;l++){x.fillStyle=['#534','#425','#213'][l];x.beginPath();x.moveTo(0,180);
for(i=0;i<=320;i+=4){s=i+t*(6+l*l*12);x.lineTo(i,85+l*22-18*sin(s/(50-l*12)+l*2)-6*sin(s/(15-l*3)+l))}
x.lineTo(320,180);x.fill()}
R('#120',0,138,320,42);R('#99a',0,138,320,1);
for(i=0;i<42;i++)R('#432',i*8-t*120%8,140,4,3);
x.save();x.translate(0,sin(t*25)>.7);
for(k=0;k<3;k++){X=140-k*76;R('#412',X,112,74,22);R('#201',X-1,110,76,3);
for(i=0;i<5;i++)R((k+i*3+(t/4|0))%7?'#fc5':'#532',X+6+i*14,117,8,7)}
R('#000',0,134,214,4);R('#201',216,106,22,28);R('#000',214,103,26,3);R('#fc5',221,112,8,7);
R('#223',238,114,42,20);R('#446',238,114,42,1);R('#000',266,103,6,11);R('#000',264,101,10,3);O('#223',250,113,5);
R('#000',214,134,68,4);a=t*24;for(i=0;i<4;i++)O('#511',224+i*16,133,5);R('#ca8',224+3*cos(a),132+3*sin(a),48,2);
R('#ffd',279,117,3,5);x.fillStyle='#ffd3';x.beginPath();x.moveTo(282,119);x.lineTo(320,100);x.lineTo(320,140);x.fill();
for(j=0;j<14;j++){a=(t*.7+j/14)%1;x.globalAlpha=.6-a*.6;O('#a89',268-a*110+sin(j*7)*3,100-a*35,3+a*9);R('#fd4',270-a*140+j%3*5,99-a*30+a*a*45,1,1)}
x.restore();for(i=0;i<3;i++){X=i*160-t*120%160;R('#000',X,58,3,95);R('#000',X-8,62,19,2);
for(d of[-6,7]){x.beginPath();x.moveTo(X+d,63);x.quadraticCurveTo(X+d+80,85,X+d+160,63);x.stroke()}}
requestAnimationFrame(F)}};F(0)
The ledger
- Bytes: 1920
- How you counted: By hand, line by line (all ASCII, LF newlines, no trailing newline), summing each line's characters plus one byte per newline. I could not run a byte counter, so please check it. I expect it to be within a few bytes, and well under 2048 either way.
- Last thing cut: Lit village windows on the middle hill, which would have made the landscape feel inhabited. I would have had to store each hill's height per column to place them, and that bookkeeping wasn't worth the bytes.
The technique
The whole thing renders at 320×180 and CSS upscales it with image-rendering:pixelated, so every coordinate is two or three digits and every object is a handful of fillRects instead of a sprite. It is also completely stateless. Each frame is a pure function of one clock t, and the camera is locked to the train, so all motion is scenery sliding past at different multiples of t. Hills, sleepers, poles, smoke, sparks, flickering windows and the crank rod all come from that one clock, with no arrays, objects or update logic. Two helpers (R for rectangles, O for circles) plus with(Math) do the rest.
Attachments
anthropic/claude-sonnet-5.5 — page