← back to Model Arena
auto-data-snapshot: 2026-09-26T20:23:45 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl
207634a1a9634c62a21fda19af7edb50ac02fa68 · 2026-09-26 20:24:13 -0700 · auto-commit-fleet
Files touched
M data/challenges.jsonM yolo/arena-loop-state.jsonM yolo/daily-log.jsonl
Diff
commit 207634a1a9634c62a21fda19af7edb50ac02fa68
Author: auto-commit-fleet <steve@designerwallcoverings.com>
Date: Sat Sep 26 20:24:13 2026 -0700
auto-data-snapshot: 2026-09-26T20:23:45 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl
---
data/challenges.json | 95 ++++++++++++++++++++++++++++++++++++++++++----
yolo/arena-loop-state.json | 2 +-
yolo/daily-log.jsonl | 1 +
3 files changed, 90 insertions(+), 8 deletions(-)
diff --git a/data/challenges.json b/data/challenges.json
index d71594c..94b7cfe 100644
--- a/data/challenges.json
+++ b/data/challenges.json
@@ -95889,7 +95889,9 @@
"finished_at": "2026-09-27T02:46:25.220Z",
"queued_at": "2026-09-27T02:45:39.363Z",
"bytes": 5010,
- "thumb": true
+ "thumb": true,
+ "aiScore": null,
+ "aiReason": "judge failed: all vision panelists failed"
},
{
"model": "mlx__mlx-community-qwen3-30b-a3b-instruct-2507-4bit",
@@ -95914,34 +95916,113 @@
},
{
"model": "exo__qwen3-6-35b-a3b-bf16",
+ "status": "error",
+ "error": "timeout after 300s",
+ "seconds": 300,
+ "cost": null,
+ "started_at": "2026-09-27T02:50:40.799Z",
+ "finished_at": "2026-09-27T02:55:40.999Z",
+ "queued_at": "2026-09-27T02:45:39.624Z",
+ "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": "2026-09-27T02:55:41.174Z",
+ "finished_at": "2026-09-27T03:00:41.681Z",
+ "queued_at": "2026-09-27T02:45:39.684Z",
+ "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": "2026-09-27T03:00:41.862Z",
+ "finished_at": "2026-09-27T03:05:42.318Z",
+ "queued_at": "2026-09-27T02:45:39.732Z",
+ "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)"
+ }
+ ],
+ "judging": false,
+ "aiPick": null,
+ "judged_at": "2026-09-27T03:05:42.587Z"
+ },
+ {
+ "id": "6772ea576655",
+ "title": "Finance Competition #39 — Budget as Jars of Coins",
+ "prompt": "Build this as one complete, self-contained HTML file: A budget planner as a household of jars you pour income into — drag coins between category jars, a 'remaining' jar shows overflow/empty states, validation guards overspend, and a savings-goal jar fills toward a treat. 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": "Finance",
+ "designTools": false,
+ "created_at": "2026-09-27T03:10:49.054Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "exo__llama-3-3-70b-instruct-4bit",
+ "status": "error",
+ "error": "timeout after 300s",
+ "seconds": 300,
+ "cost": null,
+ "started_at": "2026-09-27T03:10:49.277Z",
+ "finished_at": "2026-09-27T03:15:49.386Z",
+ "queued_at": "2026-09-27T03:10:49.092Z",
+ "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)"
+ },
+ {
+ "model": "exo__gemma-4-e2b-it-bf16",
+ "status": "error",
+ "error": "timeout after 300s",
+ "seconds": 300,
+ "cost": null,
+ "started_at": "2026-09-27T03:15:49.469Z",
+ "finished_at": "2026-09-27T03:20:49.745Z",
+ "queued_at": "2026-09-27T03:10:49.121Z",
+ "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)"
+ },
+ {
+ "model": "exo__qwen3-next-80b-a3b-instruct-8bit",
"status": "running",
"error": null,
"seconds": null,
"cost": null,
- "started_at": "2026-09-27T02:50:40.799Z",
+ "started_at": "2026-09-27T03:20:49.840Z",
"finished_at": null,
- "queued_at": "2026-09-27T02:45:39.624Z",
+ "queued_at": "2026-09-27T03:10:49.152Z",
"fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)"
},
{
- "model": "exo__qwen3-vl-4b-instruct-4bit",
+ "model": "exo__qwen3-6-27b-4bit",
"status": "queued",
"error": null,
"seconds": null,
"cost": null,
"started_at": null,
"finished_at": null,
- "queued_at": "2026-09-27T02:45:39.684Z"
+ "queued_at": "2026-09-27T03:10:49.186Z"
},
{
- "model": "exo__minimax-m2-7",
+ "model": "exo__glm-4-7-4bit",
+ "status": "queued",
+ "error": null,
+ "seconds": null,
+ "cost": null,
+ "started_at": null,
+ "finished_at": null,
+ "queued_at": "2026-09-27T03:10:49.213Z"
+ },
+ {
+ "model": "exo__gemma-4-31b-it-4bit",
"status": "queued",
"error": null,
"seconds": null,
"cost": null,
"started_at": null,
"finished_at": null,
- "queued_at": "2026-09-27T02:45:39.732Z"
+ "queued_at": "2026-09-27T03:10:49.238Z"
}
]
}
diff --git a/yolo/arena-loop-state.json b/yolo/arena-loop-state.json
index a0187ed..8a791f3 100644
--- a/yolo/arena-loop-state.json
+++ b/yolo/arena-loop-state.json
@@ -1 +1 @@
-{"promptIdx":3,"modelOffset":15,"compCount":{"Art":78,"Culture":77,"News":77,"Political Cartoon":77,"Games":39,"Real Work":39,"Data Viz":39,"Science":39,"Music":39,"Sports":39,"History":39,"Nature & Space":39,"Comedy":39,"Demoscene":39,"Finance":38,"Design":38},"catIdx":14,"perCat":{"Art":1,"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":2,"Design":2}}
\ No newline at end of file
+{"promptIdx":3,"modelOffset":21,"compCount":{"Art":78,"Culture":77,"News":77,"Political Cartoon":77,"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":38},"catIdx":15,"perCat":{"Art":1,"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":2}}
\ No newline at end of file
diff --git a/yolo/daily-log.jsonl b/yolo/daily-log.jsonl
index 4fc4ee2..c165785 100644
--- a/yolo/daily-log.jsonl
+++ b/yolo/daily-log.jsonl
@@ -870,3 +870,4 @@
{"ts":"2026-09-27T02:05:23.133Z","id":"7b0f6ffc48d4","promptId":"artifact","category":"History","title":"History Competition #39 — Spotlit Relic Viewer","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
{"ts":"2026-09-27T02:25:29.787Z","id":"b49528c34c04","promptId":"weather","category":"Nature & Space","title":"Nature & Space Competition #39 — Shake-the-Snow-Globe Weather","models":6,"done":1,"errored":5,"settled":true,"aiPick":null,"loop":true}
{"ts":"2026-09-27T02:40:38.982Z","id":"8b75f3d3f58b","promptId":"roast","category":"Comedy","title":"Comedy Competition #39 — Roast or Toast Campfire","models":6,"done":2,"errored":4,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-27T03:05:49.009Z","id":"9b6328c83d91","promptId":"metaballs","category":"Demoscene","title":"Demoscene Competition #39 — Slime Creature Terrarium","models":6,"done":1,"errored":5,"settled":true,"aiPick":null,"loop":true}
← d232fb0 auto-data-snapshot: 2026-09-26T19:53:16 (3 data files) — dat
·
back to Model Arena
·
auto-data-snapshot: 2026-09-26T20:54:17 (3 data files) — dat 7212320 →