Run Detail
completedgrok-4.6Recorded 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
668.1s
Total Tokens
48,969
Input Tokens
832
Output Tokens
48,137
Reasoning Tokens
46,818
Reasoning Effort
default
Cached Input Tokens
128
Est. Cost
$0.2903
Started
8/16/2026, 4:28:48 PM
OR Provider
xAI
Finish Reason
stop
Generation ID
gen-1786897728-6kTCA3sLZr7YfNRUPm0q
Turns (1)
Turn #1
832 in48,137 out46,818 reasoning128 cached48,969 total668.1s
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 locomotive hauls crimson carriages along an embankment at sunset — coupling rods spinning, a firebox flickering, smoke tumbling back over the roofs, telegraph poles and trees ticking past a valley of town lights.
The file
<!doctype html><body style=margin:0;overflow:hidden><canvas id=c><script>w=c.width=innerWidth;h=c.height=innerHeight;t=0;S=Math.sin;C=Math.cos;with(c.getContext`2d`)setInterval(_=>{t++;Y=h*.72;A=(x,y,r)=>{beginPath();arc(x,y,r,0,7);fill()};fillStyle='#146';fillRect(0,0,w,h);fillStyle='#e63';A(w*.7,Y-20,h/3);fillStyle='#fda';A(w*.72,Y-40,18);fillStyle='#424';beginPath();moveTo(0,h);for(i=0;i<w;i+=9)lineTo(i,Y-50+S(i*.01)*30);lineTo(w,h);fill();fillStyle='#fa5';for(i=25;i--;)fillRect(i*w/25+5,Y-55+S(i*3)*12,2,2);fillStyle='#321';fillRect(0,Y,w,h);fillStyle='#333';fillRect(0,Y+5,w,20);fillStyle='#543';for(i=0;i<w;i+=15)fillRect(i-t*4%15,Y+6,10,18);fillStyle='#99a';fillRect(0,Y+8,w,2);fillRect(0,Y+20,w,2);fillStyle='#230';for(i=w/90+2;i--;){X=i*90-t*4%90-40;fillRect(X,Y-45,5,45);A(X+2,Y-55,16)}fillStyle='#420';for(i=w/200+2;i--;){X=i*200-t*4%200-40;fillRect(X,Y-80,4,80);fillRect(X-15,Y-78,34,3);fillRect(X,Y-77,200,1)}T=w/3;fillStyle='#ffc6';beginPath();moveTo(T+130,Y-32);lineTo(T+320,Y-55);lineTo(T+320,Y-5);fill();for(j=3;j--;){fillStyle='#512';fillRect(T-80-j*85,Y-40,80,34);fillStyle='#fa6';for(k=4;k--;)fillRect(T-74-j*85+k*18,Y-34,12,10);fillStyle='#222';A(T-60-j*85,Y,7);A(T-20-j*85,Y,7)}fillStyle='#222';fillRect(T,Y-38,40,32);fillStyle='#334';fillRect(T+8,Y-36,90,28);beginPath();arc(T+53,Y-36,45,3.2,6.3);fill();fillStyle='#223';fillRect(T-5,Y-56,32,50);fillStyle='#111';fillRect(T-8,Y-60,38,6);fillStyle='#fa6';fillRect(T+2,Y-52,16,12);fillStyle='#111';fillRect(T+85,Y-66,12,30);fillRect(T+82,Y-70,18,7);fillRect(T+6,Y-50,4,7);fillRect(T+120,Y-18,16,10);fillRect(T+130,Y,15,5);beginPath();arc(T+50,Y-48,7,3.2,6.3);fill();a=t*.15;strokeStyle='#b83';for(k=3;k--;){wx=T+20+k*26;fillStyle='#222';A(wx,Y,15);stroke();beginPath();for(n=6;n--;)moveTo(wx,Y),lineTo(wx+C(a+n)*14,Y+S(a+n)*14);stroke()}lineWidth=3;beginPath();moveTo(T+20+C(a)*10,Y+S(a)*10);lineTo(T+72+C(a)*10,Y+S(a)*10);stroke();fillStyle=t%6<3?'#f40':'#fa0';fillRect(T+12,Y-18,10,8);fillStyle='#eee5';for(i=10;i--;)A(T+90-i*9+S(t/7+i)*6,Y-70-i*6,4+i)},16)</script>
The ledger
- Bytes: 2048
- How you counted: ASCII-only file, so UTF-8 bytes = characters; running total over every token from doctype through
</script>. - Last thing cut: a second, nearer hill ridge scrolling on its own sine — the extra parallax layer between valley and ballast that would have put real depth under the trees.
The technique
with(c.getContext\2d`)plus a three-argument filled-circle helperAso the sun, the tree crowns, every wheel and the trailing smoke all share onebeginPath/arc/fill` instead of paying for it at each call site — that one shape primitive is what left room for the rods, the headlight beam and the town.
Attachments
x-ai/grok-4.6 — page