← back to Model Arena
auto-data-snapshot: 2026-09-20T22:54:06 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl
6f9b1f56cb1d3899f6eb8f35e5da9f45b3474f17 · 2026-09-20 22:56:01 -0700 · auto-commit-fleet
Files touched
M data/challenges.jsonM yolo/arena-loop-state.jsonM yolo/daily-log.jsonl
Diff
commit 6f9b1f56cb1d3899f6eb8f35e5da9f45b3474f17
Author: auto-commit-fleet <steve@designerwallcoverings.com>
Date: Sun Sep 20 22:56:01 2026 -0700
auto-data-snapshot: 2026-09-20T22:54:06 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl
---
data/challenges.json | 228 ++++++++++++++++++++++++++++++++++++++++++++-
yolo/arena-loop-state.json | 2 +-
yolo/daily-log.jsonl | 4 +
3 files changed, 228 insertions(+), 6 deletions(-)
diff --git a/data/challenges.json b/data/challenges.json
index 55dea9f..1f637ff 100644
--- a/data/challenges.json
+++ b/data/challenges.json
@@ -76113,16 +76113,18 @@
"finished_at": "2026-09-21T05:21:28.019Z",
"queued_at": "2026-09-21T05:19:38.386Z",
"bytes": 7628,
- "thumb": true
+ "thumb": true,
+ "aiScore": null,
+ "aiReason": "judge failed: all vision panelists failed"
},
{
"model": "mlx__qwen3-30b-a3b-instruct-2507-4bit",
- "status": "running",
- "error": null,
- "seconds": null,
+ "status": "error",
+ "error": "timeout after 600s",
+ "seconds": 600,
"cost": null,
"started_at": "2026-09-21T05:19:38.618Z",
- "finished_at": null,
+ "finished_at": "2026-09-21T05:29:38.663Z",
"queued_at": "2026-09-21T05:19:38.428Z"
},
{
@@ -76145,6 +76147,222 @@
"finished_at": "2026-09-21T05:21:28.466Z",
"queued_at": "2026-09-21T05:19:38.507Z"
}
+ ],
+ "judging": false,
+ "aiPick": null,
+ "judged_at": "2026-09-21T05:29:38.746Z"
+ },
+ {
+ "id": "c52132a6694b",
+ "title": "Culture Competition #54 — Festivals of Nowhere",
+ "prompt": "Build this as one complete, self-contained HTML file: A world map of INVENTED holidays where hovering a region launches its signature celebration in miniature (lanterns, confetti, fireworks) and a little passport stamps each one you visit. Use realistic invented content and a strong information hierarchy. Every visible control must work and give clear feedback; include relevant empty, error, and completion states where applicable. Make it cohesive from 390px to 1440px, keyboard accessible with visible focus, and respectful of reduced motion. Be genuinely creative and surprising — surprise me with the execution, not just the concept.",
+ "category": "Culture",
+ "designTools": false,
+ "created_at": "2026-09-21T05:34:38.868Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "mlx__qwen3-next-80b-a3b-instruct-4bit",
+ "status": "error",
+ "error": "timeout after 600s",
+ "seconds": 600,
+ "cost": null,
+ "started_at": "2026-09-21T05:34:39.138Z",
+ "finished_at": "2026-09-21T05:44:39.214Z",
+ "queued_at": "2026-09-21T05:34:38.914Z"
+ },
+ {
+ "model": "exo__qwen3-coder-480b-a35b-instruct-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T05:34:39.161Z",
+ "finished_at": "2026-09-21T05:34:39.216Z",
+ "queued_at": "2026-09-21T05:34:38.961Z"
+ },
+ {
+ "model": "mac1__minicpm-v-latest",
+ "status": "error",
+ "error": "ollama bad response: 503",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T05:34:39.186Z",
+ "finished_at": "2026-09-21T05:34:39.356Z",
+ "queued_at": "2026-09-21T05:34:39.015Z"
+ },
+ {
+ "model": "exo__qwen3-5-122b-a10b-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T05:34:39.239Z",
+ "finished_at": "2026-09-21T05:34:39.273Z",
+ "queued_at": "2026-09-21T05:34:39.053Z"
+ },
+ {
+ "model": "mac1__qwen2-5vl-7b",
+ "status": "error",
+ "error": "ollama bad response: 503",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T05:34:39.379Z",
+ "finished_at": "2026-09-21T05:34:39.546Z",
+ "queued_at": "2026-09-21T05:34:39.089Z"
+ },
+ {
+ "model": "exo__gemma-4-26b-a4b-it-6bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T05:34:39.302Z",
+ "finished_at": "2026-09-21T05:34:39.331Z",
+ "queued_at": "2026-09-21T05:34:39.114Z"
+ }
+ ]
+ },
+ {
+ "id": "d6fd00bc423b",
+ "title": "News Competition #54 — Teletext Econ Briefing",
+ "prompt": "Build this as one complete, self-contained HTML file: A retro-teletext economic briefing for an INVENTED country: blocky CRT panels tick with fake indicators, a crawler scrolls, a big red/green mood dial summarizes the day — with scanlines and a channel-flip. Use realistic invented content and a strong information hierarchy. Every visible control must work and give clear feedback; include relevant empty, error, and completion states where applicable. Make it cohesive from 390px to 1440px, keyboard accessible with visible focus, and respectful of reduced motion. Be genuinely creative and surprising — surprise me with the execution, not just the concept.",
+ "category": "News",
+ "designTools": false,
+ "created_at": "2026-09-21T05:49:39.457Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "exo__qwen3-6-35b-a3b-bf16",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T05:49:39.663Z",
+ "finished_at": "2026-09-21T05:49:39.692Z",
+ "queued_at": "2026-09-21T05:49:39.493Z"
+ },
+ {
+ "model": "exo__qwen3-vl-4b-instruct-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T05:49:39.721Z",
+ "finished_at": "2026-09-21T05:49:39.760Z",
+ "queued_at": "2026-09-21T05:49:39.520Z"
+ },
+ {
+ "model": "exo__minimax-m2-7",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T05:49:39.786Z",
+ "finished_at": "2026-09-21T05:49:39.814Z",
+ "queued_at": "2026-09-21T05:49:39.549Z"
+ },
+ {
+ "model": "exo__llama-3-3-70b-instruct-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T05:49:39.837Z",
+ "finished_at": "2026-09-21T05:49:39.879Z",
+ "queued_at": "2026-09-21T05:49:39.580Z"
+ },
+ {
+ "model": "exo__gemma-4-e2b-it-bf16",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T05:49:39.926Z",
+ "finished_at": "2026-09-21T05:49:39.954Z",
+ "queued_at": "2026-09-21T05:49:39.608Z"
+ },
+ {
+ "model": "exo__qwen3-next-80b-a3b-instruct-8bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T05:49:39.978Z",
+ "finished_at": "2026-09-21T05:49:40.005Z",
+ "queued_at": "2026-09-21T05:49:39.641Z"
+ }
+ ]
+ },
+ {
+ "id": "361ae9eef0d2",
+ "title": "Political Cartoon Competition #54 — The Form to Request a Form",
+ "prompt": "Build this as one complete, self-contained HTML file: A three-panel SVG satire strip about an INVENTED bureaucratic saga (a form that requires a form to request a form). Click to advance panels; a 'plot twist' button reshuffles the punchline. Good-natured, invented characters. Use realistic invented content and a strong information hierarchy. Every visible control must work and give clear feedback; include relevant empty, error, and completion states where applicable. Make it cohesive from 390px to 1440px, keyboard accessible with visible focus, and respectful of reduced motion. Be genuinely creative and surprising — surprise me with the execution, not just the concept.",
+ "category": "Political Cartoon",
+ "designTools": false,
+ "created_at": "2026-09-21T05:54:47.766Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "exo__qwen3-6-27b-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T05:54:47.975Z",
+ "finished_at": "2026-09-21T05:54:48.002Z",
+ "queued_at": "2026-09-21T05:54:47.795Z"
+ },
+ {
+ "model": "exo__glm-4-7-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T05:54:48.028Z",
+ "finished_at": "2026-09-21T05:54:48.056Z",
+ "queued_at": "2026-09-21T05:54:47.830Z"
+ },
+ {
+ "model": "exo__gemma-4-31b-it-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T05:54:48.081Z",
+ "finished_at": "2026-09-21T05:54:48.110Z",
+ "queued_at": "2026-09-21T05:54:47.856Z"
+ },
+ {
+ "model": "exo__nvidia-nemotron-3-nano-30b-a3b-mlx-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T05:54:48.148Z",
+ "finished_at": "2026-09-21T05:54:48.179Z",
+ "queued_at": "2026-09-21T05:54:47.882Z"
+ },
+ {
+ "model": "exo__llama-3-1-nemotron-nano-4b-v1-1-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T05:54:48.216Z",
+ "finished_at": "2026-09-21T05:54:48.262Z",
+ "queued_at": "2026-09-21T05:54:47.910Z"
+ },
+ {
+ "model": "exo__qwen3-coder-next-6bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T05:54:48.309Z",
+ "finished_at": "2026-09-21T05:54:48.369Z",
+ "queued_at": "2026-09-21T05:54:47.949Z"
+ }
]
}
]
\ No newline at end of file
diff --git a/yolo/arena-loop-state.json b/yolo/arena-loop-state.json
index 17eb38d..82948de 100644
--- a/yolo/arena-loop-state.json
+++ b/yolo/arena-loop-state.json
@@ -1 +1 @@
-{"promptIdx":3,"modelOffset":4,"compCount":{"Art":55,"Culture":53,"News":53,"Political Cartoon":53,"Games":27,"Real Work":27,"Data Viz":27,"Science":27,"Music":27,"Sports":27,"History":27,"Nature & Space":27,"Comedy":27,"Demoscene":27,"Finance":27,"Design":27},"catIdx":17,"perCat":{"Art":2,"Culture":1,"News":1,"Political Cartoon":1,"Games":3,"Real Work":3,"Data Viz":3,"Science":3,"Music":3,"Sports":3,"History":3,"Nature & Space":3,"Comedy":3,"Demoscene":3,"Finance":3,"Design":3}}
\ No newline at end of file
+{"promptIdx":3,"modelOffset":22,"compCount":{"Art":55,"Culture":54,"News":54,"Political Cartoon":54,"Games":27,"Real Work":27,"Data Viz":27,"Science":27,"Music":27,"Sports":27,"History":27,"Nature & Space":27,"Comedy":27,"Demoscene":27,"Finance":27,"Design":27},"catIdx":0,"perCat":{"Art":2,"Culture":2,"News":2,"Political Cartoon":2,"Games":3,"Real Work":3,"Data Viz":3,"Science":3,"Music":3,"Sports":3,"History":3,"Nature & Space":3,"Comedy":3,"Demoscene":3,"Finance":3,"Design":3}}
\ No newline at end of file
diff --git a/yolo/daily-log.jsonl b/yolo/daily-log.jsonl
index 76889ed..a1f7831 100644
--- a/yolo/daily-log.jsonl
+++ b/yolo/daily-log.jsonl
@@ -592,3 +592,7 @@
{"ts":"2026-09-21T05:04:21.340Z","id":"9deca7cced0a","promptId":"metaballs","category":"Demoscene","title":"Demoscene Competition #27 — Slime Creature Terrarium","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
{"ts":"2026-09-21T05:09:29.619Z","id":"7a7abd2497f9","promptId":"budget","category":"Finance","title":"Finance Competition #27 — Budget as Jars of Coins","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
{"ts":"2026-09-21T05:14:38.150Z","id":"e8b57b4a2957","promptId":"formkit","category":"Design","title":"Design Competition #27 — Pre-Flight Checklist Form Kit","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-21T05:29:38.827Z","id":"b770c6c34b3b","promptId":"mondrian","category":"Art","title":"Art Competition #55 — Playable Mondrian","models":6,"done":1,"errored":5,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-21T05:44:39.430Z","id":"c52132a6694b","promptId":"culture-map","category":"Culture","title":"Culture Competition #54 — Festivals of Nowhere","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-21T05:49:47.669Z","id":"d6fd00bc423b","promptId":"econ-brief","category":"News","title":"News Competition #54 — Teletext Econ Briefing","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-21T05:54:55.979Z","id":"361ae9eef0d2","promptId":"satire-strip","category":"Political Cartoon","title":"Political Cartoon Competition #54 — The Form to Request a Form","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
← 0f3735f auto-data-snapshot: 2026-09-20T22:21:09 (3 data files) — dat
·
back to Model Arena
·
auto-data-snapshot: 2026-09-20T23:27:45 (3 data files) — dat 0014f0e →