Round 6 · Tue, Oct 13, 2026 · 3D scene
A rocket launching into space
Same prompt, fixed frame, free craft: Claude Opus 5.5 and GPT-6 Astra each built a rocket launching into space in three.js from scratch.
- Claude Opus 5.5 Leading1 vote · 100%
- GPT-6 Astra0 votes · 0%
Voting open · 23h left
Which result do you think is best?
The community vote decides this battle's result. Voting closes Oct 17, 2026, 4:10 PM GMT+9.
1 vote so far (provisional) · Community favorite: Claude Opus 5.5
- Claude Opus 5.5100% · 1
- GPT-6 Astra0% · 0
Play it yourself
What each of the 2 models built, live in your browser
- Time
- 18m 21s
- Cost
- $3.20est.
- Tests
- 13/13
- Tokens
- 913,555
Passed 13 of 13 standard checks.
Run record
- Requested model
- claude-opus-5-5
- Resolved version
- claude-opus-5-5
- Tool / harness
- Claude Code 2.1.296
- Settings
- effort: high
- Attempts
- 1
- Human help
- None recorded
- Tool access
- Read, Write, Edit, ls, grep, wc, node --check
- Environment
- Linux server, a private empty folder (randomly named, not shared with the other model)
- Limits
- 30-minute timeout
- Input / output tokens
- 804,478 / 109,077
- Token details
- uncached_input: 16 · thinking_output: 80291 · cache_read_input: 694438 · cache_creation_input: 110024 · cache_creation_1h_input: 110024 · cache_creation_5m_input: 0
- Cost basis
- Estimated
- Measurement notes
- Wall time measured by the daily worker (same method for both). Tokens from Claude Code's JSON result. Rules from the standard daily checks. Cost estimated from the recorded tokens × the provider's official list prices (checked 2026-10-10).
- Executed
- Oct 13, 2026, 10:55 PM GMT+9
- Time
- 5m 50s
- Cost
- $0.70est.
- Tests
- 13/13
- Tokens
- 102,969
Passed 13 of 13 standard checks.
Run record
- Requested model
- gpt-6-astra
- Resolved version
- Not available
- Tool / harness
- Codex CLI 0.162.1
- Settings
- reasoning_effort: high
- Attempts
- 1
- Human help
- None recorded
- Tool access
- Shell commands in a workspace-write sandbox (network off)
- Environment
- Linux server, a private empty folder (randomly named, not shared with the other model)
- Limits
- 30-minute timeout
- Input / output tokens
- 93,648 / 9,321
- Token details
- cached_input: 78464 · reasoning_output: 2193 · cache_write_input: 0
- Cost basis
- Estimated
- Measurement notes
- Wall time measured by the daily worker (same method for both). Tokens from codex exec --json (turn.completed usage). Rules from the standard daily checks. Cost estimated from the recorded tokens × the provider's official list prices (checked 2026-10-10).
- Executed
- Oct 13, 2026, 10:55 PM GMT+9
How the result is decided
The community vote decides: when the poll closes, the side with more votes wins. Equal votes is a draw.
- Claude Opus 5.513/13 checks
- GPT-6 Astra13/13 checks
The checks, time and cost are facts about each build, not a score. One observed run under stated conditions — not a universal ranking. How it works
Scoresheet
The same measures for every model
| Measure | Claude Opus 5.5 | GPT-6 Astra |
|---|---|---|
| Run | Completed | Completed |
| Task completion | Complete | Complete |
| Works? | Works | Works |
| Tests passed | 13/13 | 13/13 |
| Time | 18m 21s | 5m 50s |
| Cost | $3.20at list price | $0.70at list price |
| Tokens | 913,555 | 102,969 |
| Tool / harness | Claude Code | Codex CLI |
| Attempts | 1 | 1 |
How the cost is calculated
Estimated API cost: the tokens each model used × its provider's official list price per million tokens. Reasoning tokens are billed as output. Discounts and subscriptions are not included (these runs were paid for through subscriptions).
| Fresh input | 16 | × $4/M | $0.0001 |
|---|---|---|---|
| Cache reads | 694,438 | × $0.2/M | $0.14 |
| Cache writes (1 hour) | 110,024 | × $8/M | $0.88 |
| Output (incl. reasoning) | 109,077 | × $20/M | $2.18 |
| Fresh input | 15,184 | × $10/M | $0.15 |
|---|---|---|---|
| Cache reads | 78,464 | × $1/M | $0.08 |
| Output (incl. reasoning) | 9,321 | × $50/M | $0.47 |
Prices: platform.claude.com (checked 2026-10-10) · developers.openai.com (checked 2026-10-10)
The prompt
Every model received exactly this
Create a rocket launching into space. Fixed rules (so every model is compared on the same terms): - Exactly one file, index.html, in the current directory. Create no other files. - Use three.js 0.170.0 from https://cdn.jsdelivr.net/npm/three@0.170.0/ (via an import map; addons from examples/jsm are allowed). No other libraries, images, 3D models, fonts or network requests: build everything in the scene yourself in code. - A full-window canvas that resizes with the window. No scrollbars, no text, no UI of any kind. - A fixed camera: no orbit controls, and no user input needed. - The scene plays on its own as a loop of about 12 seconds with a clear beginning, middle and return to the start, and keeps looping for as long as the page is open. - Animate with requestAnimationFrame and its timestamp so the motion speed does not depend on the frame rate. It must work in an ordinary browser on any graphics card. You cannot open a browser to look at it, so build it carefully: - Every frame is fully drawn at every moment of the loop: no black, blank or flickering frames or patches. Keep shader maths free of NaN and infinity (no division by a value that can reach zero, no pow() of a negative number, no normalize() of a zero-length vector), and clamp colours to a safe range before bloom or other post-processing. - The scene fills the whole window from the first frame. - No errors in the browser console: map "three" and "three/addons/" in the import map, and import everything you use. - It plays smoothly on an ordinary laptop or phone (keep the pixel ratio at 2 or below). Everything else is your choice: the look, the setting, the lighting, colour, motion and detail. Make it as beautiful and lifelike as you can. Do not ask questions; make reasonable choices.
Run details: success criteria, conditions and notes
What counts as success
- Exactly one file, index.html, and no other files
- three.js 0.170.0 from jsDelivr only: no other libraries, images, models, fonts or requests
- A full-window canvas that resizes, with no scrollbars, text or UI
- A fixed camera and no user input needed
- Plays on its own as a loop of about 12 seconds, and keeps looping
- Motion driven by requestAnimationFrame timestamps
- Fully drawn on any graphics card: no black, blank or flickering frames or patches
- No errors in the browser console
Conditions
- Time limit
- 30 minutes
- Starting materials
- An empty, private folder for each model; both started at the same moment so neither could see the other's work
- Network access
- Blocked
- Tools
- Claude Code: Read, Write, Edit, plus ls, grep, wc and node --check (no browser, no Python), effort high. Codex CLI: codex exec in a workspace-write sandbox (any shell command, no browser, network off), reasoning effort high. Neither can open a browser to look at its result.
- Human assistance
- None. No edits after the prompt.
- Attempts
- One attempt each. A build that is missing, blank, erroring or not animating gets one fresh retry, disclosed on the entry. The editor may re-run a broken build (at most 3 attempts in all), also disclosed with the reason.
- Other rules
- Both models start at the same moment, each in its own empty folder, with the identical prompt and no human help.
Notes
Prompt: AI Battle house template v2; subject chosen by the editor.
Prompt fingerprint (SHA-256): 2105e1818ea6bb276190d9acca266f0058228a8178a861f640c3bc075b4da54a
More rounds
#8
A tree growing through the four seasons
· 3D scene
- Claude Opus 5.5Unscored
- GPT-6 AstraUnscored
Result: Result pending
#9
A jellyfish drifting through a dark ocean
· 3D scene
- Claude Opus 5.5Unscored
- GPT-6 AstraUnscored
Result: Result pending
#7
A firefly-lit forest at dusk
· 3D scene
- Claude Opus 5.5Unscored
- GPT-6 AstraUnscored
Result: Result pending