Claude Fable 5
via claude-code-cli 2.1.214model + harness
Run of 18 Jul 2026
3 format and presence checks passed — no check of the result
3 render and interaction checks not run
Evaluation not published
Archived pilot · Historical run
Animierte Hero (CSS-Motion)
Visual craftbuilt by GPT-5.6 Luna via codex-cli 0.144.5 model + harness
- Automated checks
- 3 format and presence checks passed — no check of the result3 render and interaction checks not run
- Judge
- Evaluation not published
- Started
- Duration
- 135 s
Artifact
Rendered by agi.jetzt from the model-produced artifactRendered offline in an isolated renderer from the stored file (sha256 776dff0dc1dd…). The file itself is not served.
Same brief, other models
Scroll sideways. Each run had its own runtime and limits — compare the artifacts, not a score.
Claude Haiku 4.5
via claude-code-cli 2.1.212model + harness
Run of 17 Jul 2026
3 format and presence checks passed — no check of the result
3 render and interaction checks not run
Evaluation not published
GPT-5.6 Sol
via codex-cli 0.144.5model + harness
Run of 17 Jul 2026
3 format and presence checks passed — no check of the result
3 render and interaction checks not run
Evaluation not published
Captured during animation: this archived single frame does not show the final state and does not assess animation or interaction.Qwen3.8-27B
via ollama 0.32.15model only
Run of 3 Sept 2026
3 format and presence checks passed — no check of the result
3 render and interaction checks not run
Evaluation not published
Automated checks
Automated checks of the stored HTML file, without running it in a browser. Details are the runner’s German originals. Format and presence checks say nothing about whether the result fulfils the brief.
| Check | Kind | Result |
|---|---|---|
| single_html5_filegenau eine HTML5-Datei | Format | Passed |
| viewport_metaViewport-Meta: 1 (erwartet 1) | Format | Passed |
| hero_with_ctaHero mit Überschrift und CTA: present (found: 2) | Presence | Present |
| no_external_requestsSandbox not available — rendering skipped | Rendering | not run |
| renders_without_console_errorsSandbox not available — rendering skipped | Rendering | not run |
| mobile_no_horizontal_overflowSandbox not available — rendering skipped | Interaction (browser) | not run |
3 render and interaction checks were not run. Recorded reason: “Sandbox not available — rendering skipped”.
Evaluation
- Deterministic score
- No score — only format and presence were checked, not the result
- Judge
- not published for this run
WhyThe v2 judge record of this run names the tested model as its own judge and lists no criteria. Its score is therefore not shown — nor the combined v2 score, which blends that judge in.
Limits of this run
- 3 render and interaction checks were not run. Whether the artifact works in a browser was not checked automatically.
- No executed check with a shown result evaluates what was built.
- No judge evaluation is published for this run. There is therefore no quality verdict — only the automated checks listed here.
- The settings shown are nominal: this runtime was called without them, so they were not enforced.
- Not fully reproducible; the recorded reason is listed under “Environment”.
Task
Brief (turn 1)
Baue eine Hero-Section als EINE einzelne HTML-Datei (Inline-CSS, optional minimal Vanilla-JS nur für Scroll-Trigger — kein Framework, kein externes Asset, keine externen Fonts) für Nebulyt — eine Plattform für Echtzeit-Wettervorhersage per Satellitendaten für die Landwirtschaft.
Die Hero muss durch Bewegung beeindrucken, nicht nur durch Layout:
- Eine markante, gestaffelte Eingangs-Animation beim Laden (CSS @keyframes): Headline, Subline und Call-to-Action erscheinen nacheinander in durchdachtem Rhythmus.
- Mindestens ein fortlaufendes, subtiles Motion-Detail (z. B. animierter Verlauf, schwebende Formen, Shimmer, Parallax beim Scrollen).
- Sauberes Easing und kontrolliertes Timing — edel und ruhig, kein hektisches Zappeln.
- `@media (prefers-reduced-motion: reduce)`: Animationen deaktivieren oder auf ein sanftes Fade reduzieren.
Inhaltlich enthalten: eine dezente Marken-/Logo-Zeile, ein starker Claim (Headline), eine erklärende Subline und genau ein klarer Call-to-Action-Button.
Stilvorgabe: Hell, atmosphärisch, wissenschaftlich-elegant. Kühles Himmelblau bis Morgenlicht-Orange als weicher Verlauf, luftige Sans-Serif, großzügige Zeilenhöhe. Motion-Idee: ziehende Wolken-/Nebelschleier im Hintergrund, ein sanft aufsteigender Sonnen-/Datenpunkt, gestaffelt eingeblendete Textzeilen. Ruhig und präzise, kein Kitsch. Zielgruppe: Betriebsleiter großer Höfe.
Responsive: sieht auf Desktop (1440px) und Mobil (390px) kontrolliert aus, kein horizontaler Overflow.From the task seed (German original); the actual prompts add output-format instructions and other wording.
Environment
- Runtime
- codex-cli 0.144.5
- Execution
- model + harnessThe model ran inside an agent harness. The result describes model + harness, not the model alone.
- Nominal profile
- std-v1 · T=0.2 · seed 7331 · 1 turn · no tools
- Profile applied?
- No — codex-cli is called without temperature, seed, token or tool settings; the values are the lab’s nominal profile.
- Reproducibility
- not fully reproducibleReasoning default and model snapshot can change on the provider side; CLI version recorded.
- Run window (runner clock)
- 2026-07-18T17:11:27+02:00 → 2026-07-18T17:13:42+02:00
Provenance
- Source system
- agi.jetzt v2 (earlier lab, imported)
- Source run
- 2026-07-18_gpt-5.6-luna_t01_s2_r3
- Status
- passed the v2 lab’s automated technical gates (“verified”)
- Run manifest (sha256)
- 252bcdab82ca44cd27f3b098e23d3496c5357a40652ef33cbe315bb73c335a74
- Artifact (sha256)
- 776dff0dc1dd81b4db579477bb5d631db336f6ba12da0d8df07ea582d5f7ed27
- Checks version
- t01-checks-v2
Model The runner’s model identifier maps to GPT-5.6 Luna in the agi.jetzt register (verified mapping).
What this is evidence for
Not an AGI measureThis run shows one thing: what a model built as a single HTML file from a precise brief. It says nothing about general intelligence.Checked automatically in this run: 3 format and presence checks passed — no check of the result · 3 render and interaction checks not run.
What the task set is meant to measure
- Artifact creation from a precise brief
- Instruction following
- Static checks of the file (no functional test)
Not in its scope
- General intelligence / AGI
- Agents and tool use
- Multimodal input
- Retrieval
- Conversation
Published and unpublished runs
5 of 14 verified v2 runs of this task are published. 5 of the 6 models with recorded runs have a published run.Not published: Phi-4-mini-instruct (1 run; 1 of 3 format and presence checks passed).Source: the selection records of the published runs. They count the task across its variants and know only models with at least one published run.