GLM-5.3 in Claude Code 2.1.280
skills off
Excluded as not a single-model result. From the run's record: A harness + model mismatch, not a model failure and not an infrastructure failure: GLM-5.3 used Claude Code's Read tool to look at a PNG render of its own work. Claude Code sends images as image input, and the text-only GLM-5.3 endpoint rejected it with HTTP 400 "This model does not support image inputs", which ended the turn before pelican_animated.svg was saved. No human turns after the prompt; not re-run.
Wall time 16m 44sCost $0.41 estimated
Review
No verdict yet.
The full review
Harness + model mismatch. A harness + model mismatch, not a model failure and not an infrastructure failure: GLM-5.3 used Claude Code's Read tool to look at a PNG render of its own work. Claude Code sends images as image input, and the text-only GLM-5.3 endpoint rejected it with HTTP 400 "This model does not support image inputs", which ended the turn before pelican_animated.svg was saved. No human turns after the prompt; not re-run.
Attempt 1 of 3
Every try of this model in this harness on this prompt, oldest first. A later attempt is the cell's result: attempt 3.
Scores
Not scored: only runs that finished on their own are scored.
Downloads
Files actually published for this run. Original output, site-made previews and post-run conversions are labelled separately.
The exact prompt
agentic harness (save the file; self-render allowed), 385 characters. Every result for this prompt
Generate an animated SVG of a pelican riding a bicycle: the wheels and pedals turn, the legs pedal in sync, and it loops seamlessly. Use only SVG/SMIL or CSS inside the SVG, no JavaScript. Save it as pelican_animated.svg in the current directory. You may render and inspect your own output (headless chromium is available at /usr/bin/chromium) and iterate on your own before finishing.
How it was made
Step by step
The prompt, every agent turn and tool call (tool name and a one-line summary; inputs and outputs are not shown), then the final message. The full machine-format transcript is published as a scrubbed download.
Show all 25 steps
Loading the timeline…
Download the full transcript Claude Code session JSONL, 344 KB. Scrubbed: anything that looks like a key, token, e-mail address or phone number is replaced, and account details and the test machine's file paths are removed.
Cost breakdown
Headline cost $0.41, estimated from the token counts at list price.
| Tokens by type | Tokens | $ per 1M | Cost |
|---|---|---|---|
| Input (uncached) | 61,312 | $1.40 | $0.0858 |
| Cache write | 0 | $0.00 | $0 |
| Cache read | 543,063 | $0.26 | $0.1412 |
| Output | 41,440 | $4.40 | $0.1823 |
| of which reasoning | not recorded | billed as output |
- Total computed from tokens
- $0.4094
- Total reported by the harness
- none
Tokens summed from the Claude Code session JSONL (per message id, incl. subagent files); if Claude Code logged zero usage for this unrecognised model, the /cost screen's per-model usage is used instead. Claude Code tags glm-5p3 as unrecognized_model and its own $ figure has costBasis unknown, so it is NOT used: cost = tokens x Fireworks GLM-5.3 price.
Prices: Fireworks GLM-5.3 serverless price (STATE.md 22:42Z; same as the OpenCode/models.dev catalog entry fireworks-ai/glm-5p3), 2026-09-23.
Run notes
- Mode: interactive TUI in tmux (160x48), inside bubblewrap sandbox
- Isolation: bwrap: private /tmp, HOME and TMPDIR inside run dir, own CLAUDE_CONFIG_DIR copy; the project files, other runs, /tmp/hx_* not mounted