Design and build Boardly's responsive, fully interactive Kanban board from the frozen prompt, rules, board data, and requirements, including pointer and keyboard drag and drop without a drag-and-drop library.
An exact model and reasoning setting per Configuration and no subagents, but no shared sandbox: Codex used its own, and Claude Code and OpenCode had none until 2026-09-24. Runs are compared only within one protocol. How the protocols differ
One archived screenshot per published Run against version 1.0.0, of the Run’s representative Revision. Ordered by setup and then by repetition, not by quality.
Frozen with this version. Requirement IDs are stable across versions and are cited unchanged by evaluation records.
Automated checks are not an accessibility certification. Recorded axe findings describe what the tooling observed at capture time, on a pinned browser and viewport. A check that reports no violation is not proof that the interface is accessible, and a selector problem is inconclusive rather than an implementation failure.
| # | Model | Tool | Revision | Status | Actions |
|---|---|---|---|---|---|
| Fig. 01 | Claude Fable 5.1 (medium) | Claude Code | 0 · initial | live | |
| Fig. 02 | Claude Opus 5.5 (medium) | Claude Code | 0 · initial | live | |
| Fig. 03 | GPT-6-Astra (medium) | Codex CLI | 0 · initial | live | |
| Fig. 04 | GPT-6-Luna (max) | Codex CLI | 0 · initial | live | |
| Fig. 05 | GPT-6-Sol (high) | Codex CLI | 0 · initial | live |
Fig. 01Claude Fable 5.1 (medium)
Fig. 02Claude Opus 5.5 (medium)
Operator-attested: the Configuration, tool version, displayed model, and elapsed time were recorded by the operator from what the tool showed at Run time. They are not independently verified. An exact model ID appears only when the tool exposed one; it is never inferred.
Published sites are independent, AI-generated demos served from separate preview origins with local mock data. They are not products, and no UIBenchmark session data crosses to them.
Exact model ID, tool version, elapsed time, run state, stop reason, discarded attempts and every published Revision, repairs included, in run log order. Each Run and each Revision links to its own page.
01Run 1 · Claude Fable 5.1 (medium) · Claude Code
These Runs were executed against version 1.0.0, the most recently frozen Challenge Version under protocol v2. Runs against another frozen Version are listed on that Version’s own page, because they received different inputs.
Design and build Boardly's responsive, fully interactive Kanban board from the frozen prompt, rules, board data, and requirements, including pointer and keyboard drag and drop without a drag-and-drop library.
Fictional team project-management tool, Kanban board view
The workflow designs the interface itself from the frozen brief.
Read PROMPT.md and BENCHMARK_RULES.mdThis is the brief of the most recently frozen Challenge Version under protocol v2. The full text of its launch prompt and shared rules, and the frozen inputs of earlier versions, are on the Challenge Version pages, so nothing here is a paraphrase of what a Run actually received.
The declared rules and viewports version 1.0.0 was executed and captured under.
Fig. 03GPT-6-Astra (medium)
Fig. 04GPT-6-Luna (max)
Fig. 05GPT-6-Sol (high)
02Run 1 · Claude Opus 5.5 (medium) · Claude Code
03Run 1 · GPT-6-Astra (medium) · Codex CLI
04Run 1 · GPT-6-Luna (max) · Codex CLI
05Run 1 · GPT-6-Sol (high) · Codex CLI
Discarded attempts failed for a technical reason — a crashed session, a tool outage, a broken upload — and were discarded and retried from the same frozen inputs. The count is not a quality signal.
Generation cost: Not separately metered. Runs were executed on the operator’s personal tool subscriptions, which do not itemize a per-Run charge. No amount is attributed, and no zero-cost claim is made.
Starter and asset hashes are published so every run can be shown to have received the same bytes. There is no starter download and no asset download.
Starter SHA-256
5d7f9d0d76c136e32134fd4a23cbbf219a650b742aabfa3a6e4a11b0ac25c108
Asset pack SHA-256
d098bf9ed5103f51ac70c32a2363ba3e0b88276acd6a858ab7530efe37c6e3dc