← back to Model Arena
auto-data-snapshot: 2026-09-27T02:30:26 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl
af97759319a1ca17c703bcccacbc4c023e5ee8ea · 2026-09-27 02:30:55 -0700 · auto-commit-fleet
Files touched
M data/challenges.jsonM yolo/arena-loop-state.jsonM yolo/daily-log.jsonl
Diff
commit af97759319a1ca17c703bcccacbc4c023e5ee8ea
Author: auto-commit-fleet <steve@designerwallcoverings.com>
Date: Sun Sep 27 02:30:55 2026 -0700
auto-data-snapshot: 2026-09-27T02:30:26 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl
---
data/challenges.json | 104 +++++++++++++++++++++++++++++++++++++++++----
yolo/arena-loop-state.json | 2 +-
yolo/daily-log.jsonl | 1 +
3 files changed, 98 insertions(+), 9 deletions(-)
diff --git a/data/challenges.json b/data/challenges.json
index e92c949..0f4b30b 100644
--- a/data/challenges.json
+++ b/data/challenges.json
@@ -96733,23 +96733,111 @@
"runs": [
{
"model": "qwen3-14b",
- "status": "running",
+ "status": "done",
"error": null,
- "seconds": null,
- "cost": null,
+ "seconds": 173,
+ "cost": 0,
"started_at": "2026-09-27T09:00:05.604Z",
- "finished_at": null,
- "queued_at": "2026-09-27T09:00:05.475Z"
+ "finished_at": "2026-09-27T09:02:58.158Z",
+ "queued_at": "2026-09-27T09:00:05.475Z",
+ "bytes": 11839,
+ "thumb": true,
+ "aiScore": null,
+ "aiReason": "judge failed: all vision panelists failed"
},
{
"model": "qwen25-7b",
- "status": "queued",
+ "status": "done",
+ "error": null,
+ "seconds": 38,
+ "cost": 0,
+ "started_at": "2026-09-27T09:02:58.316Z",
+ "finished_at": "2026-09-27T09:03:36.695Z",
+ "queued_at": "2026-09-27T09:00:05.537Z",
+ "bytes": 5371,
+ "thumb": true,
+ "aiScore": null,
+ "aiReason": "judge failed: all vision panelists failed"
+ }
+ ],
+ "judging": false,
+ "aiPick": null,
+ "judged_at": "2026-09-27T09:04:02.515Z"
+ },
+ {
+ "id": "5b15c17380c0",
+ "title": "Games Competition #40 — Comet Snake in a Dying Galaxy",
+ "prompt": "Build this as one complete, self-contained HTML file: Snake, but the snake is a comet and the arena is a shrinking galaxy: eating stars grows your tail AND bends gravity, near-misses trigger slow-mo, and the high score is logged as a named 'constellation'. 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": "2026-09-27T09:02:29.289Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "exo__llama-3-2-1b-instruct-4bit",
+ "status": "error",
+ "error": "timeout after 300s",
+ "seconds": 300,
+ "cost": null,
+ "started_at": "2026-09-27T09:02:29.624Z",
+ "finished_at": "2026-09-27T09:07:29.795Z",
+ "queued_at": "2026-09-27T09:02:29.385Z",
+ "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)"
+ },
+ {
+ "model": "exo__qwen3-coder-next-8bit",
+ "status": "error",
+ "error": "timeout after 300s",
+ "seconds": 300,
+ "cost": null,
+ "started_at": "2026-09-27T09:07:29.843Z",
+ "finished_at": "2026-09-27T09:12:30.078Z",
+ "queued_at": "2026-09-27T09:02:29.423Z",
+ "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)"
+ },
+ {
+ "model": "exo__qwen3-6-35b-a3b-4bit",
+ "status": "error",
+ "error": "timeout after 300s",
+ "seconds": 300,
+ "cost": null,
+ "started_at": "2026-09-27T09:12:30.131Z",
+ "finished_at": "2026-09-27T09:17:30.386Z",
+ "queued_at": "2026-09-27T09:02:29.458Z",
+ "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)"
+ },
+ {
+ "model": "exo__qwen3-5-9b-8bit",
+ "status": "error",
+ "error": "timeout after 300s",
+ "seconds": 300,
+ "cost": null,
+ "started_at": "2026-09-27T09:17:30.486Z",
+ "finished_at": "2026-09-27T09:22:30.890Z",
+ "queued_at": "2026-09-27T09:02:29.493Z",
+ "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)"
+ },
+ {
+ "model": "exo__qwen3-235b-a22b-instruct-2507-4bit",
+ "status": "error",
+ "error": "timeout after 300s",
+ "seconds": 300,
+ "cost": null,
+ "started_at": "2026-09-27T09:22:31.188Z",
+ "finished_at": "2026-09-27T09:27:31.815Z",
+ "queued_at": "2026-09-27T09:02:29.537Z",
+ "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)"
+ },
+ {
+ "model": "exo__qwen3-5-122b-a10b-bf16",
+ "status": "running",
"error": null,
"seconds": null,
"cost": null,
- "started_at": null,
+ "started_at": "2026-09-27T09:27:31.859Z",
"finished_at": null,
- "queued_at": "2026-09-27T09:00:05.537Z"
+ "queued_at": "2026-09-27T09:02:29.577Z",
+ "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)"
}
]
}
diff --git a/yolo/arena-loop-state.json b/yolo/arena-loop-state.json
index 7eedf6b..2f3de53 100644
--- a/yolo/arena-loop-state.json
+++ b/yolo/arena-loop-state.json
@@ -1 +1 @@
-{"promptIdx":3,"modelOffset":75,"compCount":{"Art":80,"Culture":79,"News":79,"Political Cartoon":79,"Games":39,"Real Work":39,"Data Viz":39,"Science":39,"Music":39,"Sports":39,"History":39,"Nature & Space":39,"Comedy":39,"Demoscene":39,"Finance":39,"Design":39},"catIdx":4,"perCat":{"Art":3,"Culture":3,"News":3,"Political Cartoon":3,"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":81,"compCount":{"Art":80,"Culture":79,"News":79,"Political Cartoon":79,"Games":40,"Real Work":39,"Data Viz":39,"Science":39,"Music":39,"Sports":39,"History":39,"Nature & Space":39,"Comedy":39,"Demoscene":39,"Finance":39,"Design":39},"catIdx":5,"perCat":{"Art":3,"Culture":3,"News":3,"Political Cartoon":3,"Games":1,"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 74bae05..ef47635 100644
--- a/yolo/daily-log.jsonl
+++ b/yolo/daily-log.jsonl
@@ -881,3 +881,4 @@
{"ts":"2026-09-27T07:47:08.325Z","id":"05fc8ebb4fe9","promptId":"languages","category":"Culture","title":"Culture Competition #79 — The Last Speaker","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
{"ts":"2026-09-27T08:22:18.635Z","id":"3eeca9af985e","promptId":"news-ticker","category":"News","title":"News Competition #79 — Absurd 24-Hour News","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
{"ts":"2026-09-27T08:57:28.883Z","id":"faace762ff30","promptId":"metaphor","category":"Political Cartoon","title":"Political Cartoon Competition #79 — Ship of State by Committee","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-27T09:04:02.990Z","id":"fcf664ddbe62","promptId":"compare","title":"Daily · Decision Tools: Model Comparison Console","done":2,"aiPick":null,"partial":false}
← 61cafdf auto-data-snapshot: 2026-09-27T01:59:50 (2 data files) — dat
·
back to Model Arena
·
auto-data-snapshot: 2026-09-27T03:00:59 (3 data files) — dat fa13df0 →