← back to Model Arena
auto-data-snapshot: 2026-09-21T19:40:08 (2 data files) — data/challenges.json yolo/daily-log.jsonl
8e7c757151143edee40d6ecb8f92bc0c34e53942 · 2026-09-21 19:48:49 -0700 · auto-commit-fleet
Files touched
M data/challenges.jsonM yolo/daily-log.jsonl
Diff
commit 8e7c757151143edee40d6ecb8f92bc0c34e53942
Author: auto-commit-fleet <steve@designerwallcoverings.com>
Date: Mon Sep 21 19:48:49 2026 -0700
auto-data-snapshot: 2026-09-21T19:40:08 (2 data files) — data/challenges.json yolo/daily-log.jsonl
---
data/challenges.json | 175 +++++++++++++++++++++++++++++++++++++++++++--------
yolo/daily-log.jsonl | 1 +
2 files changed, 149 insertions(+), 27 deletions(-)
diff --git a/data/challenges.json b/data/challenges.json
index 465f5e1..160c7fd 100644
--- a/data/challenges.json
+++ b/data/challenges.json
@@ -88424,13 +88424,13 @@
{
"model": "mlx__qwen3-30b-a3b-instruct-2507-4bit",
"status": "error",
- "error": "server restarted mid-run",
+ "error": "server restarted mid-run (gave up after 4 resumes)",
"seconds": 0,
"cost": null,
"started_at": "2026-09-21T22:54:01.170Z",
"finished_at": null,
"queued_at": "2026-09-21T22:54:00.942Z",
- "resumes": 3
+ "resumes": 5
},
{
"model": "exo__minimax-m2-7-4bit",
@@ -90034,8 +90034,7 @@
"started_at": "2026-09-22T01:13:19.288Z",
"finished_at": "2026-09-22T01:21:18.462Z",
"queued_at": "2026-09-22T01:10:16.623Z",
- "bytes": 20178,
- "thumb": true
+ "bytes": 20178
},
{
"model": "qwen25-7b",
@@ -90107,8 +90106,7 @@
"started_at": "2026-09-22T01:21:19.686Z",
"finished_at": "2026-09-22T01:23:25.625Z",
"queued_at": "2026-09-22T01:13:12.829Z",
- "bytes": 7097,
- "thumb": true
+ "bytes": 7097
},
{
"model": "qwen25-7b",
@@ -90218,8 +90216,7 @@
"started_at": "2026-09-22T01:27:06.841Z",
"finished_at": "2026-09-22T01:29:58.737Z",
"queued_at": "2026-09-22T01:26:27.606Z",
- "bytes": 9682,
- "thumb": true
+ "bytes": 9682
},
{
"model": "qwen25-7b",
@@ -90251,8 +90248,7 @@
"started_at": "2026-09-22T01:29:59.054Z",
"finished_at": "2026-09-22T01:33:03.159Z",
"queued_at": "2026-09-22T01:28:35.358Z",
- "bytes": 10373,
- "thumb": true
+ "bytes": 10373
},
{
"model": "qwen25-7b",
@@ -90304,8 +90300,7 @@
"started_at": "2026-09-22T01:33:03.823Z",
"finished_at": "2026-09-22T01:35:58.158Z",
"queued_at": "2026-09-22T01:32:08.425Z",
- "bytes": 10242,
- "thumb": true
+ "bytes": 10242
},
{
"model": "qwen25-7b",
@@ -90357,8 +90352,7 @@
"started_at": "2026-09-22T01:35:59.112Z",
"finished_at": "2026-09-22T01:39:20.794Z",
"queued_at": "2026-09-22T01:35:03.923Z",
- "bytes": 10880,
- "thumb": true
+ "bytes": 10880
},
{
"model": "qwen25-7b",
@@ -90430,8 +90424,7 @@
"started_at": "2026-09-22T01:39:22.066Z",
"finished_at": "2026-09-22T01:41:42.973Z",
"queued_at": "2026-09-22T01:38:07.831Z",
- "bytes": 8914,
- "thumb": true
+ "bytes": 8914
},
{
"model": "qwen25-7b",
@@ -90788,27 +90781,155 @@
},
{
"model": "qwen3-14b",
+ "status": "done",
+ "error": null,
+ "seconds": 226,
+ "cost": 0,
+ "started_at": "2026-09-22T02:00:26.831Z",
+ "finished_at": "2026-09-22T02:04:12.977Z",
+ "queued_at": "2026-09-22T01:59:49.841Z",
+ "bytes": 13417
+ },
+ {
+ "model": "qwen25-7b",
"status": "error",
- "error": "server restarted mid-run",
+ "error": "ollama bad response: 503",
"seconds": 0,
"cost": null,
- "started_at": "2026-09-22T02:00:26.831Z",
- "finished_at": null,
- "queued_at": "2026-09-22T01:59:49.841Z",
- "resumes": 1
+ "started_at": "2026-09-22T02:04:13.013Z",
+ "finished_at": "2026-09-22T02:04:13.287Z",
+ "queued_at": "2026-09-22T01:59:49.873Z"
+ }
+ ]
+ },
+ {
+ "id": "d00cbd8540ac",
+ "title": "Data Viz Competition #37 — City of Data Dashboard",
+ "prompt": "Build this as one complete, self-contained HTML file: An INVENTED 'city of data' dashboard where bar charts are skyscrapers, a donut is a roundabout, and a line chart is the dusk skyline — one shared filter re-zones the whole city, with a legend and an empty 'ghost town' state. 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": "Data Viz",
+ "designTools": false,
+ "created_at": "2026-09-22T02:02:29.377Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "mac1__minicpm-v-latest",
+ "status": "error",
+ "error": "ollama bad response: 503",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-22T02:04:13.323Z",
+ "finished_at": "2026-09-22T02:04:13.546Z",
+ "queued_at": "2026-09-22T02:02:29.401Z"
+ },
+ {
+ "model": "mac1__qwen2-5vl-7b",
+ "status": "error",
+ "error": "ollama bad response: 503",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-22T02:04:13.577Z",
+ "finished_at": "2026-09-22T02:04:13.868Z",
+ "queued_at": "2026-09-22T02:02:29.417Z"
+ },
+ {
+ "model": "qwen3-14b",
+ "status": "done",
+ "error": null,
+ "seconds": 165,
+ "cost": 0,
+ "started_at": "2026-09-22T02:04:13.894Z",
+ "finished_at": "2026-09-22T02:06:58.795Z",
+ "queued_at": "2026-09-22T02:02:29.437Z",
+ "bytes": 9552
},
{
"model": "qwen25-7b",
"status": "error",
- "error": "server restarted mid-run",
+ "error": "ollama bad response: 503",
"seconds": 0,
"cost": null,
- "started_at": null,
- "finished_at": null,
- "queued_at": "2026-09-22T01:59:49.873Z",
- "resumes": 1
+ "started_at": "2026-09-22T02:06:58.811Z",
+ "finished_at": "2026-09-22T02:06:59.026Z",
+ "queued_at": "2026-09-22T02:02:29.455Z"
+ }
+ ]
+ },
+ {
+ "id": "fb473706aec1",
+ "title": "Music Competition #37 — Constellation Sequencer",
+ "prompt": "Build this as one complete, self-contained HTML file: A Web Audio step sequencer where the grid is a night sky and each active step is a star that flickers on its beat (patterns = constellations); tempo, swing, per-track mute, a shooting-star fill, and a safe muted default. 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": "Music",
+ "designTools": false,
+ "created_at": "2026-09-22T02:05:31.397Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "qwen3-14b",
+ "status": "done",
+ "error": null,
+ "seconds": 318,
+ "cost": 0,
+ "started_at": "2026-09-22T02:06:59.039Z",
+ "finished_at": "2026-09-22T02:12:16.923Z",
+ "queued_at": "2026-09-22T02:05:31.412Z",
+ "bytes": 16801,
+ "thumb": true,
+ "aiScore": null,
+ "aiReason": "judge failed: all vision panelists failed"
+ },
+ {
+ "model": "exo__minimax-m2-7-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-22T02:05:31.596Z",
+ "finished_at": "2026-09-22T02:05:32.026Z",
+ "queued_at": "2026-09-22T02:05:31.424Z"
+ },
+ {
+ "model": "qwen25-7b",
+ "status": "error",
+ "error": "ollama bad response: 503",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-22T02:12:16.938Z",
+ "finished_at": "2026-09-22T02:12:17.231Z",
+ "queued_at": "2026-09-22T02:05:31.475Z"
+ },
+ {
+ "model": "exo__qwen3-coder-480b-a35b-instruct-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-22T02:05:32.046Z",
+ "finished_at": "2026-09-22T02:05:32.177Z",
+ "queued_at": "2026-09-22T02:05:31.487Z"
+ },
+ {
+ "model": "mac1__minicpm-v-latest",
+ "status": "error",
+ "error": "ollama bad response: 503",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-22T02:12:17.245Z",
+ "finished_at": "2026-09-22T02:12:17.444Z",
+ "queued_at": "2026-09-22T02:05:31.499Z"
+ },
+ {
+ "model": "exo__qwen3-5-122b-a10b-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-22T02:05:32.197Z",
+ "finished_at": "2026-09-22T02:05:32.427Z",
+ "queued_at": "2026-09-22T02:05:31.528Z"
}
],
- "aiPick": null
+ "judging": false,
+ "aiPick": null,
+ "judged_at": "2026-09-22T02:12:25.542Z"
}
]
\ No newline at end of file
diff --git a/yolo/daily-log.jsonl b/yolo/daily-log.jsonl
index 5922f50..070beb7 100644
--- a/yolo/daily-log.jsonl
+++ b/yolo/daily-log.jsonl
@@ -809,3 +809,4 @@
{"ts":"2026-09-22T02:00:31.017Z","id":"036f6cb02824","promptId":"solar","category":"Science","title":"Science Competition #37 — Conduct the Solar System","models":4,"done":1,"errored":3,"settled":true,"aiPick":null,"loop":true}
{"ts":"2026-09-22T02:04:14.332Z","id":"48cbc3899440","promptId":"sequencer","category":"Music","title":"Music Competition #37 — Constellation Sequencer","models":4,"done":1,"errored":3,"settled":true,"aiPick":null,"loop":true}
{"ts":"2026-09-22T02:07:01.826Z","id":"d00cbd8540ac","promptId":"multi-chart","category":"Data Viz","title":"Data Viz Competition #37 — City of Data Dashboard","models":4,"done":1,"errored":3,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-22T02:12:19.874Z","id":"fb473706aec1","promptId":"sequencer","category":"Music","title":"Music Competition #37 — Constellation Sequencer","models":6,"done":1,"errored":5,"settled":true,"aiPick":null,"loop":true}
← a7f303c auto-data-snapshot: 2026-09-21T17:27:28 (3 data files) — dat
·
back to Model Arena
·
auto-data-snapshot: 2026-09-22T09:54:34 (3 data files) — dat 8fb3efb →