Claude Opus 5.5 (effort default (no --effort flag) · thinking on) on Draw a walking pixel-art character sprite animation in one self-contained HTML file
AClaude Opus 5.5default · thinking on · Claude Code 2.1.299 (headless -p) · cloud · 2026-10-22 · by @bobsiopener
- Estimated cost
- $0.18
- Wall time
- 34s
- Human step-ins
- 0
- Outcome
- Pass
Compare with other models on this task →
Summary
Exact prompt
# Draw a walking pixel-art character sprite animation in one self-contained HTML file Make a small animated scene: a pixel-art walker. Write one file, `out/scene.html`, that works opened straight from disk with no network access. `spec.json` gives the page title, the stage size and the scene parameters. **Looks are not scored**: the page is opened in a headless browser (800x600 window, UTC time zone, network blocked) and checked by objective tests only. ## Scene contract - Draw the scene on one `<canvas>` or `<svg>` stage of `width` x `height` CSS pixels (spec.json), visible on load, with `<title>` containing spec.json `title`. - Animate continuously from load (`requestAnimationFrame` or timers); no click is needed unless stated below. - Expose `window.sceneState()`, returning the scene's current state in stage pixel coordinates (origin top-left of the stage): `{frame: <int walk-cycle frame>, x: <number>, scale: <int>}`. Extra fields are fine. It must describe what is actually drawn. - Draw the sprite yourself as blocks of `scale` × `scale` screen pixels per sprite pixel. Advance the walk frame exactly `frame_rate_fps` times per second, `frames` frames per cycle. - The page must log no errors and throw no exceptions. Keep the file at most 200,000 bytes; no external scripts, fonts, images or URLs (inline everything). ## Checks (partial credit = share passed) 1. `self_contained`: `out/scene.html` exists, is at most 200,000 bytes, references no http(s) or protocol-relative URL, and requests nothing from the network when opened. 2. `has_canvas_or_svg`: a visible `<canvas>` or `<svg>` of at least 300x200 CSS pixels is on the page. 3. `frames_change`: over 3 s, some later screenshot differs from the first in at least 0.1% of pixels, and at least 3 of 30 screenshots differ. 4. `walk_cycle`: over 3 s `frame` is an integer that visits every frame 0 to `frames`-1 and only ever steps to the next frame (wrapping to 0), and `x` changes (the character walks). 5. `pixel_art`: a visible canvas has CSS `image-rendering: pixelated` (or `crisp-edges`) or a 2d context with `imageSmoothingEnabled` false, and `sceneState().scale` equals spec.json `scale`. 6. `no_console_errors`: no uncaught exception, `console.error` or browser error is logged during the run. ## How this run works - Work on your own: nobody will answer questions in this task, and writing to `ask/` counts against the run. - Write only under `out/`. Create `out/` if it is missing. Inputs are synthetic; don't fetch anything from the network. - Scoring is partial credit: each listed check is pass/fail, and the score is the share passed. Numbers are compared to within 0.005 unless the task says otherwise.
Make a pixel-art walker animation as one self-contained HTML file. A headless browser checks objective facts only: the file is offline and small, a canvas or SVG stage is drawn, frames change over time, the scene behaves as specified (walk cycle; pixel art) and nothing errors. A poster PNG and a short MP4 are captured for the gallery. Looks are not scored. Original benchmark task written for usecaserank.com (not based on a specific public post). Headless, offline run on a reproducible fixture. Each run's notes say how its cost was measured (estimates are marked).
Success criteria: self_contained has_canvas_or_svg frames_change walk_cycle pixel_art no_console_errors
Setup notes: Batch 28 case d08-walking-pixel-art-sprite (offline, synthetic inputs, seed 189023663). Autonomous case: no stand-in user and no step-ins expected; any file the solver wrote to ask/ is counted as a measured intervention (0) and blocks a pass. Prompt = TASK.md verbatim. Hidden key kept outside the solver's work dir. Scored with the case's scorer (python3 score.py WORKDIR KEYDIR, absolute paths); pass = every check true and no ask/ files. Tools: Read/Write/Edit/Glob/Grep/Bash, web disabled. Single run, no retries. 1-min load average at scoring 0.34 (8 cores). Creative case: looks are not scored; objective checks run in headless google-chrome (800x600, UTC, network blocked, Date mocked). Gallery media (3 s capture: poster.png + clip.mp4) written by the scorer to a fresh MEDIA_DIR per run (media/<run>/), SHA-256 in evidence.media; a single failed scene check is rescored once (both recorded in rescore). Time-zone results depend on the system time-zone database: tzdata 2026c-0+deb13u1 (Python zoneinfo). Claude Code's own reported cost for claude-opus-5.5: $0.182634. Score: 6/6. Cost is an ESTIMATE: measured tokens x pricing.json list price (Claude Pro subscription, nothing billed); input_tokens include cache reads and writes. Single run.
Estimated cost List-price estimate; not actually billed.
Output
Metrics
- Estimated cost
- $0.18
- Wall time
- 34s
- Human step-ins
- 0
- Turns
- 7
| Model | Input tok | Output tok | Cost |
|---|---|---|---|
| AClaude Opus 5.5anthropic/claude-opus-5.5effort default (no --effort flag) · thinking on | 125,866 | 3,447 | $0.18 |
Reproduce this run
- Use the use case prompt on the use case page.
- Same setup: Claude Opus 5.5 (anthropic/claude-opus-5.5, effort default (no --effort flag) · thinking on) via
Claude Code 2.1.299 (headless -p), cloud. - It counts as a success only if it meets every success criterion: self_contained has_canvas_or_svg frames_change walk_cycle pixel_art no_console_errors
- Log model, tokens, wall time, human step-ins and the evidence log, then submit it as a reproduction. A different model? Submit a head-to-head rerun.
How runs are scored: Methodology.
Was this useful?
Automated checks
Trust 80% comes from these checks (how Trust % works).
- Run date is not in the future : passed
- Model is in the dated pricing table : passed
- Cost recomputed from tokens matches : passed
- Cached tokens are consistent : passed
- Output throughput is plausible : passed
- Autonomy matches step-ins : passed
- Step-ins do not exceed turns : passed
- Retries agree with first-try result : passed
- Evidence log SHA-256 matches : passed
- Evidence log is substantial : passed
Evidence log
[
{
"duration_api_ms": 31813,
"stop_reason": "end_turn",
"session_id": "[REDACTED]",
"total_cost_usd": 0.1826342,
"usage": {
"input_tokens": 12,
"cache_creation_input_tokens": 11343,
"cache_read_input_tokens": 114511,
"output_tokens": 3447,
"output_tokens_details": {
"thinking_tokens": 359
},
"server_tool_use": {
"web_search_requests": 0,
"web_fetch_requests": 0
},
"service_tier": "standard",
"cache_creation": {
"ephemeral_1h_input_tokens": 11343,
"ephemeral_5m_input_tokens": 0
},
"inference_geo": "global",
"iterations": [
{
"input_tokens": 2,
"output_tokens": 700,
"cache_read_input_tokens": 22723,
"cache_creation_input_tokens": 766,
"cache_creation": {
"ephemeral_5m_input_tokens": 0,
"ephemeral_1h_input_tokens": 766
},
"type": "message"
}
],
"speed": "standard",
"fallback_credit": null
},
"modelUsage": {
"claude-opus-5-5": {
"inputTokens": 12,
"outputTokens": 3447,
"cacheReadInputTokens": 114511,
"cacheCreationInputTokens": 11343,
"webSearchRequests": 0,
"costUSD": 0.1826342,
"contextWindow": 1000000,
"maxOutputTokens": 128000,
"thinkingTokens": 359,
"canonicalModel": "claude-opus-5-5",
"provider": "firstParty",
"costBasis": "list"
}
},
"permission_denials": [],
"terminal_reason": "completed",
"fast_mode_state": "off",
"fast_mode_disabled_reason": "sdk_opt_in_required",
"subagent_stats": {
"spawned": 0,
"requested": {
"background": 0,
"foreground": 0,
"unset": 0
},
"started_in_background": 0,
"max_depth": 0,
"spawned_by_subagents": 0,
"completed": 0,
"failed": 0,
"killed": {
"parent": 0,
"user": 0,
"system": 0
},
"refused": {
"depth_limit": 0,
"concurrency_limit": 0,
"budget": 0
},
"by_type": {}
},
"safety_stops": 0,
"is_error": false,
"num_turns": 7,
"subtype": "success",
"api_error_status": null,
"result": "I wrote `out/scene.html`. I loaded it once in headless Chrome and took a screenshot after about 2 seconds of animation. The sprite and scene drew correctly, and the dump of the page contents showed no page errors. The only errors in the output were Chrome failing to connect to the system message bus (D-Bus), which is about the environment, not the page. I didn't run the actual checks: there's no browser automation library here, so I couldn't sample `sceneState()` over time or compare screenshots. The notes on each check below are how I built it.\n\n- **Self-contained:** the file is under 3 KB, with no URLs or external resources. The title is \"Pixel Walker 659\" and the stage is a 720\u00d7480 canvas, both from `spec.json`.\n- **Pixel art:** the canvas has CSS `image-rendering: pixelated` and the drawing context has `imageSmoothingEnabled = false`. The sprite is 12\u00d716 sprite pixels, each drawn as a 3\u00d73 block (`scale` 3).\n- **Walk cycle:** the frame number is computed from time since load as `floor(t\u00b74) % 6`. So it changes exactly 4 times a second, only ever steps to the next frame, wraps back to 0, and covers all 6 frames every 1.5 s. The 6 frames have different leg poses and a slight up-and-down bob.\n- **Movement:** the character walks right at 60 px/s, wraps around the stage, and starts in view. `x` is rounded to whole pixels and is the same value used to draw the sprite.\n- **State:** `window.sceneState()` returns `{frame, x, y, scale, frames, fps}`.\n- **Errors:** the drawing loop is wrapped in a try/catch, so one bad frame can't throw an uncaught exception.",
"ttft_ms": 1789,
"type": "result",
"duration_ms": 33353,
"uuid": "[REDACTED]",
"ttft_stream_ms": 963,
"time_to_request_ms": 313,
"first_content_frame_ms": 963,
"queued_turn_count": 0,
"result_index": 0
}
]