← back to Model Arena
auto-data-snapshot: 2026-09-25T12:23:56 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl
ae020b82d85391fdeed3a9347a064a793ebdf1b3 · 2026-09-25 12:24:25 -0700 · auto-commit-fleet
Files touched
M data/challenges.jsonM yolo/arena-loop-state.jsonM yolo/daily-log.jsonl
Diff
commit ae020b82d85391fdeed3a9347a064a793ebdf1b3
Author: auto-commit-fleet <steve@designerwallcoverings.com>
Date: Fri Sep 25 12:24:25 2026 -0700
auto-data-snapshot: 2026-09-25T12:23:56 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl
---
data/challenges.json | 153 +++++++++++++++++++++++++++++++++++++++++++++
yolo/arena-loop-state.json | 2 +-
yolo/daily-log.jsonl | 1 +
3 files changed, 155 insertions(+), 1 deletion(-)
diff --git a/data/challenges.json b/data/challenges.json
index 915c10f..1a57cf9 100644
--- a/data/challenges.json
+++ b/data/challenges.json
@@ -93522,5 +93522,158 @@
"bytes": 14909
}
]
+ },
+ {
+ "id": "acc2c9f4a253",
+ "title": "Political Cartoon Competition #75 — Ship of State by Committee",
+ "prompt": "Build this as one complete, self-contained HTML file: A single bold SVG metaphor illustration for an INVENTED political theme — 'the ship of state steered by committee' — where dragging elements changes the metaphor's meaning and the caption adapts. Light/dark toggle. 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": "2026-09-25T18:59:04.621Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "mlx__qwen3-30b-a3b-instruct-2507-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 300,
+ "cost": null,
+ "started_at": "2026-09-25T18:59:05.828Z",
+ "finished_at": "2026-09-25T19:04:06.164Z",
+ "queued_at": "2026-09-25T18:59:05.387Z",
+ "fellBack": "http://127.0.0.1:52415 (mlx-community/MiniMax-M2.7-4bit)"
+ },
+ {
+ "model": "exo__minimax-m2-7-4bit",
+ "status": "error",
+ "error": "timeout after 300s",
+ "seconds": 300,
+ "cost": null,
+ "started_at": "2026-09-25T18:59:05.942Z",
+ "finished_at": "2026-09-25T19:04:06.309Z",
+ "queued_at": "2026-09-25T18:59:05.561Z",
+ "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3-30B-A3B-Instruct-2507-4bit)"
+ },
+ {
+ "model": "qwen25-7b",
+ "status": "done",
+ "error": null,
+ "seconds": 24,
+ "cost": 0,
+ "started_at": "2026-09-25T18:59:05.989Z",
+ "finished_at": "2026-09-25T18:59:30.126Z",
+ "queued_at": "2026-09-25T18:59:05.630Z",
+ "bytes": 3197
+ },
+ {
+ "model": "mlx__qwen3-next-80b-a3b-instruct-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 300,
+ "cost": null,
+ "started_at": "2026-09-25T19:04:06.206Z",
+ "finished_at": "2026-09-25T19:09:06.611Z",
+ "queued_at": "2026-09-25T18:59:05.671Z",
+ "fellBack": "http://127.0.0.1:52415 (mlx-community/Qwen3-Next-80B-A3B-Instruct-4bit)"
+ },
+ {
+ "model": "exo__qwen3-coder-480b-a35b-instruct-4bit",
+ "status": "error",
+ "error": "timeout after 300s",
+ "seconds": 301,
+ "cost": null,
+ "started_at": "2026-09-25T19:04:06.436Z",
+ "finished_at": "2026-09-25T19:09:07.184Z",
+ "queued_at": "2026-09-25T18:59:05.709Z",
+ "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3-30B-A3B-Instruct-2507-4bit)"
+ },
+ {
+ "model": "mac1__minicpm-v-latest",
+ "status": "done",
+ "error": null,
+ "seconds": 8,
+ "cost": 0,
+ "started_at": "2026-09-25T18:59:31.535Z",
+ "finished_at": "2026-09-25T18:59:39.996Z",
+ "queued_at": "2026-09-25T18:59:05.760Z",
+ "bytes": 487
+ }
+ ]
+ },
+ {
+ "id": "cd267a104b77",
+ "title": "Games Competition #38 — Wake the Dragon Breakout",
+ "prompt": "Build this as one complete, self-contained HTML file: Brick-breaker where the bricks are a sleeping dragon's scales — knock them loose and the dragon slowly wakes (eyes open, breathing quickens). The paddle is a shield; a caught power-up briefly lets you paint new bricks. 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": "Games",
+ "designTools": false,
+ "created_at": "2026-09-25T19:14:10.032Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "mlx__qwen3-8-27b-8bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 300,
+ "cost": null,
+ "started_at": "2026-09-25T19:14:10.556Z",
+ "finished_at": "2026-09-25T19:19:10.996Z",
+ "queued_at": "2026-09-25T19:14:10.120Z",
+ "fellBack": "http://127.0.0.1:52415 (mlx-community/MiniMax-M2.7-4bit)"
+ },
+ {
+ "model": "exo__qwen3-5-122b-a10b-4bit",
+ "status": "error",
+ "error": "timeout after 300s",
+ "seconds": 300,
+ "cost": null,
+ "started_at": "2026-09-25T19:14:10.633Z",
+ "finished_at": "2026-09-25T19:19:11.102Z",
+ "queued_at": "2026-09-25T19:14:10.203Z",
+ "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3-30B-A3B-Instruct-2507-4bit)"
+ },
+ {
+ "model": "mac1__qwen2-5vl-7b",
+ "status": "done",
+ "error": null,
+ "seconds": 30,
+ "cost": 0,
+ "started_at": "2026-09-25T19:14:10.744Z",
+ "finished_at": "2026-09-25T19:14:40.787Z",
+ "queued_at": "2026-09-25T19:14:10.276Z",
+ "bytes": 2760
+ },
+ {
+ "model": "mlx__mlx-community-qwen3-30b-a3b-instruct-2507-4bit",
+ "status": "error",
+ "error": "timeout after 300s",
+ "seconds": 300,
+ "cost": null,
+ "started_at": "2026-09-25T19:19:11.053Z",
+ "finished_at": "2026-09-25T19:24:11.270Z",
+ "queued_at": "2026-09-25T19:14:10.334Z"
+ },
+ {
+ "model": "exo__gemma-4-26b-a4b-it-6bit",
+ "status": "error",
+ "error": "timeout after 300s",
+ "seconds": 300,
+ "cost": null,
+ "started_at": "2026-09-25T19:19:11.159Z",
+ "finished_at": "2026-09-25T19:24:11.355Z",
+ "queued_at": "2026-09-25T19:14:10.412Z",
+ "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3-30B-A3B-Instruct-2507-4bit)"
+ },
+ {
+ "model": "exo__qwen3-6-35b-a3b-bf16",
+ "status": "running",
+ "error": null,
+ "seconds": null,
+ "cost": null,
+ "started_at": "2026-09-25T19:24:11.415Z",
+ "finished_at": null,
+ "queued_at": "2026-09-25T19:14:10.481Z",
+ "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3-30B-A3B-Instruct-2507-4bit)"
+ }
+ ]
}
]
\ No newline at end of file
diff --git a/yolo/arena-loop-state.json b/yolo/arena-loop-state.json
index ea92790..814e343 100644
--- a/yolo/arena-loop-state.json
+++ b/yolo/arena-loop-state.json
@@ -1 +1 @@
-{"promptIdx":3,"modelOffset":2,"compCount":{"Art":76,"Culture":75,"News":75,"Political Cartoon":74,"Games":37,"Real Work":37,"Data Viz":37,"Science":37,"Music":37,"Sports":37,"History":37,"Nature & Space":37,"Comedy":37,"Demoscene":37,"Finance":37,"Design":37},"catIdx":3,"perCat":{"Art":3,"Culture":3,"News":3,"Political Cartoon":2,"Games":1,"Real Work":1,"Data Viz":1,"Science":1,"Music":1,"Sports":1,"History":1,"Nature & Space":1,"Comedy":1,"Demoscene":1,"Finance":1,"Design":1}}
\ No newline at end of file
+{"promptIdx":3,"modelOffset":14,"compCount":{"Art":76,"Culture":75,"News":75,"Political Cartoon":75,"Games":38,"Real Work":37,"Data Viz":37,"Science":37,"Music":37,"Sports":37,"History":37,"Nature & Space":37,"Comedy":37,"Demoscene":37,"Finance":37,"Design":37},"catIdx":5,"perCat":{"Art":3,"Culture":3,"News":3,"Political Cartoon":3,"Games":2,"Real Work":1,"Data Viz":1,"Science":1,"Music":1,"Sports":1,"History":1,"Nature & Space":1,"Comedy":1,"Demoscene":1,"Finance":1,"Design":1}}
\ No newline at end of file
diff --git a/yolo/daily-log.jsonl b/yolo/daily-log.jsonl
index cf7c85f..083fcf0 100644
--- a/yolo/daily-log.jsonl
+++ b/yolo/daily-log.jsonl
@@ -841,3 +841,4 @@
{"ts":"2026-09-22T16:14:37.534Z","id":"a9a068b218b6","promptId":"kinetic-type","category":"Art","title":"Art Competition #76 — Swarm Typography Poster","models":4,"done":4,"errored":0,"settled":true,"aiPick":null,"loop":true}
{"ts":"2026-09-22T16:19:00.766Z","id":"0715b25a41dd","promptId":"languages","category":"Culture","title":"Culture Competition #75 — The Last Speaker","models":4,"done":4,"errored":0,"settled":true,"aiPick":null,"loop":true}
{"ts":"2026-09-22T16:24:34.034Z","id":"74a9c3f65798","promptId":"news-ticker","category":"News","title":"News Competition #75 — Absurd 24-Hour News","models":4,"done":4,"errored":0,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-25T19:09:09.664Z","id":"acc2c9f4a253","promptId":"metaphor","category":"Political Cartoon","title":"Political Cartoon Competition #75 — Ship of State by Committee","models":6,"done":2,"errored":4,"settled":true,"aiPick":null,"loop":true}
← eb07ab5 auto-data-snapshot: 2026-09-25T10:52:57 (1 data files) — dat
·
back to Model Arena
·
auto-data-snapshot: 2026-09-25T12:54:38 (3 data files) — dat 8af60a1 →