← back to Model Arena
auto-data-snapshot: 2026-09-26T20:54:17 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl
721232017f66c99336ba9877d2a5d3ffcf7c50d2 · 2026-09-26 20:54:43 -0700 · auto-commit-fleet
Files touched
M data/challenges.jsonM yolo/arena-loop-state.jsonM yolo/daily-log.jsonl
Diff
commit 721232017f66c99336ba9877d2a5d3ffcf7c50d2
Author: auto-commit-fleet <steve@designerwallcoverings.com>
Date: Sat Sep 26 20:54:43 2026 -0700
auto-data-snapshot: 2026-09-26T20:54:17 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl
---
data/challenges.json | 92 ++++++++++++++++++++++++++++++++++++++++++----
yolo/arena-loop-state.json | 2 +-
yolo/daily-log.jsonl | 1 +
3 files changed, 86 insertions(+), 9 deletions(-)
diff --git a/data/challenges.json b/data/challenges.json
index 94b7cfe..4634136 100644
--- a/data/challenges.json
+++ b/data/challenges.json
@@ -95985,44 +95985,120 @@
},
{
"model": "exo__qwen3-next-80b-a3b-instruct-8bit",
+ "status": "error",
+ "error": "timeout after 300s",
+ "seconds": 300,
+ "cost": null,
+ "started_at": "2026-09-27T03:20:49.840Z",
+ "finished_at": "2026-09-27T03:25:50.107Z",
+ "queued_at": "2026-09-27T03:10:49.152Z",
+ "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)"
+ },
+ {
+ "model": "exo__qwen3-6-27b-4bit",
+ "status": "error",
+ "error": "timeout after 300s",
+ "seconds": 300,
+ "cost": null,
+ "started_at": "2026-09-27T03:25:50.307Z",
+ "finished_at": "2026-09-27T03:30:50.973Z",
+ "queued_at": "2026-09-27T03:10:49.186Z",
+ "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)"
+ },
+ {
+ "model": "exo__glm-4-7-4bit",
+ "status": "error",
+ "error": "timeout after 300s",
+ "seconds": 300,
+ "cost": null,
+ "started_at": "2026-09-27T03:30:51.222Z",
+ "finished_at": "2026-09-27T03:35:51.617Z",
+ "queued_at": "2026-09-27T03:10:49.213Z",
+ "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)"
+ },
+ {
+ "model": "exo__gemma-4-31b-it-4bit",
+ "status": "error",
+ "error": "timeout after 300s",
+ "seconds": 300,
+ "cost": null,
+ "started_at": "2026-09-27T03:35:51.810Z",
+ "finished_at": "2026-09-27T03:40:52.351Z",
+ "queued_at": "2026-09-27T03:10:49.238Z",
+ "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)"
+ }
+ ]
+ },
+ {
+ "id": "ab18d0f08b1c",
+ "title": "Design Competition #39 — Pre-Flight Checklist Form Kit",
+ "prompt": "Build this as one complete, self-contained HTML file: An accessible form kit framed as a spaceship pre-flight checklist — validation states light up like console gauges, an inline error summary is the 'do not launch' panel, an optional multi-step flow, and rock-solid keyboard focus. 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": "2026-09-27T03:45:59.474Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "exo__nvidia-nemotron-3-nano-30b-a3b-mlx-4bit",
+ "status": "error",
+ "error": "timeout after 300s",
+ "seconds": 300,
+ "cost": null,
+ "started_at": "2026-09-27T03:45:59.867Z",
+ "finished_at": "2026-09-27T03:51:00.067Z",
+ "queued_at": "2026-09-27T03:45:59.524Z",
+ "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)"
+ },
+ {
+ "model": "exo__llama-3-1-nemotron-nano-4b-v1-1-4bit",
"status": "running",
"error": null,
"seconds": null,
"cost": null,
- "started_at": "2026-09-27T03:20:49.840Z",
+ "started_at": "2026-09-27T03:51:00.330Z",
"finished_at": null,
- "queued_at": "2026-09-27T03:10:49.152Z",
+ "queued_at": "2026-09-27T03:45:59.569Z",
"fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)"
},
{
- "model": "exo__qwen3-6-27b-4bit",
+ "model": "exo__qwen3-coder-next-6bit",
"status": "queued",
"error": null,
"seconds": null,
"cost": null,
"started_at": null,
"finished_at": null,
- "queued_at": "2026-09-27T03:10:49.186Z"
+ "queued_at": "2026-09-27T03:45:59.629Z"
},
{
- "model": "exo__glm-4-7-4bit",
+ "model": "exo__step-3-5-flash-6bit",
"status": "queued",
"error": null,
"seconds": null,
"cost": null,
"started_at": null,
"finished_at": null,
- "queued_at": "2026-09-27T03:10:49.213Z"
+ "queued_at": "2026-09-27T03:45:59.711Z"
},
{
- "model": "exo__gemma-4-31b-it-4bit",
+ "model": "exo__qwen3-next-80b-a3b-thinking-4bit",
+ "status": "queued",
+ "error": null,
+ "seconds": null,
+ "cost": null,
+ "started_at": null,
+ "finished_at": null,
+ "queued_at": "2026-09-27T03:45:59.764Z"
+ },
+ {
+ "model": "exo__deepseek-v3-1-4bit",
"status": "queued",
"error": null,
"seconds": null,
"cost": null,
"started_at": null,
"finished_at": null,
- "queued_at": "2026-09-27T03:10:49.238Z"
+ "queued_at": "2026-09-27T03:45:59.821Z"
}
]
}
diff --git a/yolo/arena-loop-state.json b/yolo/arena-loop-state.json
index 8a791f3..7c8bf51 100644
--- a/yolo/arena-loop-state.json
+++ b/yolo/arena-loop-state.json
@@ -1 +1 @@
-{"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
+{"promptIdx":3,"modelOffset":27,"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":39},"catIdx":16,"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":3}}
\ No newline at end of file
diff --git a/yolo/daily-log.jsonl b/yolo/daily-log.jsonl
index c165785..f47019c 100644
--- a/yolo/daily-log.jsonl
+++ b/yolo/daily-log.jsonl
@@ -871,3 +871,4 @@
{"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}
+{"ts":"2026-09-27T03:40:59.379Z","id":"6772ea576655","promptId":"budget","category":"Finance","title":"Finance Competition #39 — Budget as Jars of Coins","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
← 207634a auto-data-snapshot: 2026-09-26T20:23:45 (3 data files) — dat
·
back to Model Arena
·
auto-data-snapshot: 2026-09-26T21:24:47 (3 data files) — dat efc8392 →