← back to Model Arena
auto-data-snapshot: 2026-09-27T22:09:52 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl
be08c17e7fc309db833aa0f3020ae0cc333d1186 · 2026-09-27 22:10:18 -0700 · auto-commit-fleet
Files touched
M data/challenges.jsonM yolo/arena-loop-state.jsonM yolo/daily-log.jsonl
Diff
commit be08c17e7fc309db833aa0f3020ae0cc333d1186
Author: auto-commit-fleet <steve@designerwallcoverings.com>
Date: Sun Sep 27 22:10:18 2026 -0700
auto-data-snapshot: 2026-09-27T22:09:52 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl
---
data/challenges.json | 203 +++++++++++++++++++++++++++++++++++++++++++++
yolo/arena-loop-state.json | 2 +-
yolo/daily-log.jsonl | 2 +
3 files changed, 206 insertions(+), 1 deletion(-)
diff --git a/data/challenges.json b/data/challenges.json
index 8977bd9..ac1bc82 100644
--- a/data/challenges.json
+++ b/data/challenges.json
@@ -99282,5 +99282,208 @@
"judging": false,
"aiPick": null,
"judged_at": "2026-09-28T04:33:08.243Z"
+ },
+ {
+ "id": "559bc69196d0",
+ "title": "Culture Competition #82 — 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": "2026-09-28T04:38:07.450Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "mac1__qwen2-5vl-7b",
+ "status": "done",
+ "error": null,
+ "seconds": 41,
+ "cost": 0,
+ "started_at": "2026-09-28T04:39:58.606Z",
+ "finished_at": "2026-09-28T04:40:54.430Z",
+ "queued_at": "2026-09-28T04:38:25.772Z",
+ "bytes": 5570
+ },
+ {
+ "model": "qwen3-14b",
+ "status": "done",
+ "error": null,
+ "seconds": 223,
+ "cost": 0,
+ "started_at": "2026-09-28T04:41:06.913Z",
+ "finished_at": "2026-09-28T04:45:14.402Z",
+ "queued_at": "2026-09-28T04:38:51.217Z",
+ "bytes": 10571
+ },
+ {
+ "model": "qwen25-7b",
+ "status": "done",
+ "error": null,
+ "seconds": 45,
+ "cost": 0,
+ "started_at": "2026-09-28T04:45:58.028Z",
+ "finished_at": "2026-09-28T04:47:10.276Z",
+ "queued_at": "2026-09-28T04:39:02.237Z",
+ "bytes": 4469
+ },
+ {
+ "model": "mac1__minicpm-v-latest",
+ "status": "done",
+ "error": null,
+ "seconds": 75,
+ "cost": 0,
+ "started_at": "2026-09-28T04:47:42.926Z",
+ "finished_at": "2026-09-28T04:49:47.662Z",
+ "queued_at": "2026-09-28T04:39:21.971Z",
+ "bytes": 3168
+ }
+ ]
+ },
+ {
+ "id": "e7c6f87cedb0",
+ "title": "News Competition #82 — 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": "2026-09-28T04:56:10.648Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "qwen25-7b",
+ "status": "done",
+ "error": null,
+ "seconds": 22,
+ "cost": 0,
+ "started_at": "2026-09-28T04:56:11.244Z",
+ "finished_at": "2026-09-28T04:56:33.601Z",
+ "queued_at": "2026-09-28T04:56:10.874Z",
+ "bytes": 3407,
+ "thumb": true,
+ "aiScore": null,
+ "aiReason": "judge failed: all vision panelists failed"
+ },
+ {
+ "model": "mac1__minicpm-v-latest",
+ "status": "done",
+ "error": null,
+ "seconds": 9,
+ "cost": 0,
+ "started_at": "2026-09-28T04:56:33.646Z",
+ "finished_at": "2026-09-28T04:56:42.912Z",
+ "queued_at": "2026-09-28T04:56:10.937Z",
+ "bytes": 1037,
+ "thumb": true,
+ "aiScore": null,
+ "aiReason": "judge failed: all vision panelists failed"
+ },
+ {
+ "model": "mac1__qwen2-5vl-7b",
+ "status": "done",
+ "error": null,
+ "seconds": 38,
+ "cost": 0,
+ "started_at": "2026-09-28T04:56:42.945Z",
+ "finished_at": "2026-09-28T04:57:21.236Z",
+ "queued_at": "2026-09-28T04:56:11.021Z",
+ "bytes": 4535,
+ "thumb": true,
+ "aiScore": null,
+ "aiReason": "judge failed: all vision panelists failed"
+ },
+ {
+ "model": "qwen3-14b",
+ "status": "done",
+ "error": null,
+ "seconds": 153,
+ "cost": 0,
+ "started_at": "2026-09-28T04:57:21.274Z",
+ "finished_at": "2026-09-28T04:59:54.035Z",
+ "queued_at": "2026-09-28T04:56:11.073Z",
+ "bytes": 8340,
+ "thumb": true,
+ "aiScore": null,
+ "aiReason": "judge failed: all vision panelists failed"
+ }
+ ],
+ "judging": false,
+ "aiPick": null,
+ "judged_at": "2026-09-28T05:00:08.877Z"
+ },
+ {
+ "id": "703c8ad78a77",
+ "title": "Political Cartoon Competition #82 — 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": "2026-09-28T05:04:55.525Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "qwen25-7b",
+ "status": "done",
+ "error": null,
+ "seconds": 30,
+ "cost": 0,
+ "started_at": "2026-09-28T05:04:56.093Z",
+ "finished_at": "2026-09-28T05:05:26.034Z",
+ "queued_at": "2026-09-28T05:04:55.622Z",
+ "bytes": 3786,
+ "thumb": true
+ },
+ {
+ "model": "mlx__qwen3-30b-a3b-instruct-2507-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 300,
+ "cost": null,
+ "started_at": "2026-09-28T05:04:56.200Z",
+ "finished_at": "2026-09-28T05:09:56.405Z",
+ "queued_at": "2026-09-28T05:04:55.704Z",
+ "fellBack": "http://127.0.0.1:52415 (mlx-community/MiniMax-M2.7-4bit)"
+ },
+ {
+ "model": "exo__qwen3-coder-480b-a35b-instruct-4bit",
+ "status": "error",
+ "error": "timeout after 300s",
+ "seconds": 301,
+ "cost": null,
+ "started_at": "2026-09-28T05:04:56.246Z",
+ "finished_at": "2026-09-28T05:09:57.025Z",
+ "queued_at": "2026-09-28T05:04:55.786Z",
+ "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3-Next-80B-A3B-Instruct-4bit)"
+ },
+ {
+ "model": "mac1__minicpm-v-latest",
+ "status": "done",
+ "error": null,
+ "seconds": 13,
+ "cost": 0,
+ "started_at": "2026-09-28T05:05:26.110Z",
+ "finished_at": "2026-09-28T05:05:39.074Z",
+ "queued_at": "2026-09-28T05:04:55.865Z",
+ "bytes": 757,
+ "thumb": true
+ },
+ {
+ "model": "mlx__qwen3-8-27b-8bit",
+ "status": "running",
+ "error": null,
+ "seconds": null,
+ "cost": null,
+ "started_at": "2026-09-28T05:09:56.465Z",
+ "finished_at": null,
+ "queued_at": "2026-09-28T05:04:55.947Z"
+ },
+ {
+ "model": "exo__qwen3-5-122b-a10b-4bit",
+ "status": "running",
+ "error": null,
+ "seconds": null,
+ "cost": null,
+ "started_at": "2026-09-28T05:09:57.087Z",
+ "finished_at": null,
+ "queued_at": "2026-09-28T05:04:56.017Z",
+ "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3-Next-80B-A3B-Instruct-4bit)"
+ }
+ ]
}
]
\ No newline at end of file
diff --git a/yolo/arena-loop-state.json b/yolo/arena-loop-state.json
index 0ea2f8b..fd9a57c 100644
--- a/yolo/arena-loop-state.json
+++ b/yolo/arena-loop-state.json
@@ -1 +1 @@
-{"promptIdx":3,"modelOffset":11,"compCount":{"Art":83,"Culture":81,"News":81,"Political Cartoon":81,"Games":41,"Real Work":41,"Data Viz":41,"Science":41,"Music":41,"Sports":41,"History":41,"Nature & Space":41,"Comedy":41,"Demoscene":41,"Finance":41,"Design":41},"catIdx":17,"perCat":{"Art":2,"Culture":1,"News":1,"Political Cartoon":1,"Games":2,"Real Work":2,"Data Viz":2,"Science":2,"Music":2,"Sports":2,"History":2,"Nature & Space":2,"Comedy":2,"Demoscene":2,"Finance":2,"Design":2}}
\ No newline at end of file
+{"promptIdx":3,"modelOffset":9,"compCount":{"Art":83,"Culture":82,"News":82,"Political Cartoon":82,"Games":41,"Real Work":41,"Data Viz":41,"Science":41,"Music":41,"Sports":41,"History":41,"Nature & Space":41,"Comedy":41,"Demoscene":41,"Finance":41,"Design":41},"catIdx":0,"perCat":{"Art":2,"Culture":2,"News":2,"Political Cartoon":2,"Games":2,"Real Work":2,"Data Viz":2,"Science":2,"Music":2,"Sports":2,"History":2,"Nature & Space":2,"Comedy":2,"Demoscene":2,"Finance":2,"Design":2}}
\ No newline at end of file
diff --git a/yolo/daily-log.jsonl b/yolo/daily-log.jsonl
index 2339368..b011724 100644
--- a/yolo/daily-log.jsonl
+++ b/yolo/daily-log.jsonl
@@ -913,3 +913,5 @@
{"ts":"2026-09-28T04:00:30.023Z","id":"2e454c06f75f","promptId":"candles","category":"Finance","title":"Finance Competition #41 — Meme-Stock Chart With a Personality","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
{"ts":"2026-09-28T04:15:48.431Z","id":"22d4d22c67fb","promptId":"tokens","category":"Design","title":"Design Competition #41 — Palette & Type Mad-Lab","models":6,"done":2,"errored":4,"settled":true,"aiPick":null,"loop":true}
{"ts":"2026-09-28T04:32:29.745Z","id":"6d00e2148cdd","promptId":"mondrian","category":"Art","title":"Art Competition #83 — Playable Mondrian","models":6,"done":2,"errored":4,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-28T04:51:10.284Z","id":"559bc69196d0","promptId":"culture-map","category":"Culture","title":"Culture Competition #82 — Festivals of Nowhere","models":4,"done":4,"errored":0,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-28T04:59:55.448Z","id":"e7c6f87cedb0","promptId":"econ-brief","category":"News","title":"News Competition #82 — Teletext Econ Briefing","models":4,"done":4,"errored":0,"settled":true,"aiPick":null,"loop":true}
← 6a517b1 auto-data-snapshot: 2026-09-27T21:30:02 (3 data files) — dat
·
back to Model Arena
·
auto-data-snapshot: 2026-09-27T22:40:22 (3 data files) — dat 7639ad7 →