← back to Model Arena
auto-data-snapshot: 2026-09-27T08:08:22 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl
41fd04e327093101591cee95c2c7f29c50b89409 · 2026-09-27 08:08:46 -0700 · auto-commit-fleet
Files touched
M data/challenges.jsonM yolo/arena-loop-state.jsonM yolo/daily-log.jsonl
Diff
commit 41fd04e327093101591cee95c2c7f29c50b89409
Author: auto-commit-fleet <steve@designerwallcoverings.com>
Date: Sun Sep 27 08:08:46 2026 -0700
auto-data-snapshot: 2026-09-27T08:08:22 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl
---
data/challenges.json | 106 ++++++++++++++++++++++++++++++++++++++++-----
yolo/arena-loop-state.json | 2 +-
yolo/daily-log.jsonl | 1 +
3 files changed, 97 insertions(+), 12 deletions(-)
diff --git a/data/challenges.json b/data/challenges.json
index 5446f28..2158699 100644
--- a/data/challenges.json
+++ b/data/challenges.json
@@ -97582,26 +97582,29 @@
"finished_at": "2026-09-27T14:29:06.764Z",
"queued_at": "2026-09-27T14:28:51.114Z",
"bytes": 1577,
- "thumb": true
+ "thumb": true,
+ "aiScore": null,
+ "aiReason": "judge failed: all vision panelists failed"
},
{
"model": "mlx__qwen3-next-80b-a3b-instruct-4bit",
- "status": "running",
- "error": null,
- "seconds": null,
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 300,
"cost": null,
"started_at": "2026-09-27T14:33:51.648Z",
- "finished_at": null,
- "queued_at": "2026-09-27T14:28:51.186Z"
+ "finished_at": "2026-09-27T14:38:51.900Z",
+ "queued_at": "2026-09-27T14:28:51.186Z",
+ "fellBack": "http://127.0.0.1:52415 (mlx-community/Qwen3-Next-80B-A3B-Instruct-4bit)"
},
{
"model": "exo__qwen3-5-122b-a10b-4bit",
- "status": "running",
- "error": null,
- "seconds": null,
+ "status": "error",
+ "error": "timeout after 300s",
+ "seconds": 300,
"cost": null,
"started_at": "2026-09-27T14:33:51.732Z",
- "finished_at": null,
+ "finished_at": "2026-09-27T14:38:51.950Z",
"queued_at": "2026-09-27T14:28:51.232Z",
"fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)"
},
@@ -97615,7 +97618,88 @@
"finished_at": "2026-09-27T14:29:56.058Z",
"queued_at": "2026-09-27T14:28:51.270Z",
"bytes": 4628,
- "thumb": true
+ "thumb": true,
+ "aiScore": null,
+ "aiReason": "judge failed: all vision panelists failed"
+ }
+ ],
+ "judging": false,
+ "aiPick": null,
+ "judged_at": "2026-09-27T14:38:52.092Z"
+ },
+ {
+ "id": "7ca928b659b7",
+ "title": "Design Competition #40 — Design System Safari",
+ "prompt": "Build this as one complete, self-contained HTML file: A UI component kit staged as a 'design system safari' — each component (buttons, inputs, tabs, modal, toast, cards) lives in a themed habitat card, a live light/dark toggle changes the biome, and every accessible state is shown. 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": "Design",
+ "designTools": false,
+ "created_at": "2026-09-27T14:44:00.017Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "mlx__mlx-community-qwen3-30b-a3b-instruct-2507-4bit",
+ "status": "error",
+ "error": "timeout after 300s",
+ "seconds": 300,
+ "cost": null,
+ "started_at": "2026-09-27T14:44:00.361Z",
+ "finished_at": "2026-09-27T14:49:00.481Z",
+ "queued_at": "2026-09-27T14:44:00.090Z"
+ },
+ {
+ "model": "exo__gemma-4-26b-a4b-it-6bit",
+ "status": "error",
+ "error": "timeout after 300s",
+ "seconds": 300,
+ "cost": null,
+ "started_at": "2026-09-27T14:44:00.407Z",
+ "finished_at": "2026-09-27T14:49:00.647Z",
+ "queued_at": "2026-09-27T14:44:00.140Z",
+ "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)"
+ },
+ {
+ "model": "exo__qwen3-6-35b-a3b-bf16",
+ "status": "error",
+ "error": "timeout after 300s",
+ "seconds": 300,
+ "cost": null,
+ "started_at": "2026-09-27T14:49:00.755Z",
+ "finished_at": "2026-09-27T14:54:00.946Z",
+ "queued_at": "2026-09-27T14:44:00.181Z",
+ "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)"
+ },
+ {
+ "model": "exo__qwen3-vl-4b-instruct-4bit",
+ "status": "error",
+ "error": "timeout after 300s",
+ "seconds": 300,
+ "cost": null,
+ "started_at": "2026-09-27T14:54:01.033Z",
+ "finished_at": "2026-09-27T14:59:01.218Z",
+ "queued_at": "2026-09-27T14:44:00.219Z",
+ "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)"
+ },
+ {
+ "model": "exo__minimax-m2-7",
+ "status": "error",
+ "error": "timeout after 300s",
+ "seconds": 300,
+ "cost": null,
+ "started_at": "2026-09-27T14:59:01.256Z",
+ "finished_at": "2026-09-27T15:04:01.387Z",
+ "queued_at": "2026-09-27T14:44:00.257Z",
+ "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)"
+ },
+ {
+ "model": "exo__llama-3-3-70b-instruct-4bit",
+ "status": "running",
+ "error": null,
+ "seconds": null,
+ "cost": null,
+ "started_at": "2026-09-27T15:04:01.542Z",
+ "finished_at": null,
+ "queued_at": "2026-09-27T14:44:00.293Z",
+ "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 f376792..ef34d15 100644
--- a/yolo/arena-loop-state.json
+++ b/yolo/arena-loop-state.json
@@ -1 +1 @@
-{"promptIdx":3,"modelOffset":10,"compCount":{"Art":80,"Culture":79,"News":79,"Political Cartoon":79,"Games":40,"Real Work":40,"Data Viz":40,"Science":40,"Music":40,"Sports":40,"History":40,"Nature & Space":40,"Comedy":40,"Demoscene":40,"Finance":40,"Design":39},"catIdx":15,"perCat":{"Art":3,"Culture":3,"News":3,"Political Cartoon":3,"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":3}}
\ No newline at end of file
+{"promptIdx":3,"modelOffset":16,"compCount":{"Art":80,"Culture":79,"News":79,"Political Cartoon":79,"Games":40,"Real Work":40,"Data Viz":40,"Science":40,"Music":40,"Sports":40,"History":40,"Nature & Space":40,"Comedy":40,"Demoscene":40,"Finance":40,"Design":40},"catIdx":16,"perCat":{"Art":3,"Culture":3,"News":3,"Political Cartoon":3,"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
diff --git a/yolo/daily-log.jsonl b/yolo/daily-log.jsonl
index 376ed8c..cc40f0e 100644
--- a/yolo/daily-log.jsonl
+++ b/yolo/daily-log.jsonl
@@ -892,3 +892,4 @@
{"ts":"2026-09-27T13:33:38.200Z","id":"455616d6262c","promptId":"starmap","category":"Nature & Space","title":"Nature & Space Competition #40 — Invent Your Own Constellations","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
{"ts":"2026-09-27T14:03:44.091Z","id":"3eb8fde07f2c","promptId":"meme","category":"Comedy","title":"Comedy Competition #40 — The Meme Generator That Fights Back","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
{"ts":"2026-09-27T14:23:50.849Z","id":"083feec65fb6","promptId":"plasma","category":"Demoscene","title":"Demoscene Competition #40 — Lava-Lamp Boot Screen","models":6,"done":2,"errored":4,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-27T14:38:59.940Z","id":"6aa278ada14d","promptId":"portfolio","category":"Finance","title":"Finance Competition #40 — Galactic Exchange Portfolio","models":6,"done":2,"errored":4,"settled":true,"aiPick":null,"loop":true}
← 8695a1f auto-data-snapshot: 2026-09-27T07:37:50 (3 data files) — dat
·
back to Model Arena
·
auto-data-snapshot: 2026-09-27T08:38:51 (3 data files) — dat d6fe4bd →