← back to Model Arena
auto-data-snapshot: 2026-09-27T01:59:50 (2 data files) — data/challenges.json yolo/daily-log.jsonl
61cafdf95947b643fc3ccb4f5625aaf9c8dea5b1 · 2026-09-27 02:00:22 -0700 · auto-commit-fleet
Files touched
M data/challenges.jsonM yolo/daily-log.jsonl
Diff
commit 61cafdf95947b643fc3ccb4f5625aaf9c8dea5b1
Author: auto-commit-fleet <steve@designerwallcoverings.com>
Date: Sun Sep 27 02:00:22 2026 -0700
auto-data-snapshot: 2026-09-27T01:59:50 (2 data files) — data/challenges.json yolo/daily-log.jsonl
---
data/challenges.json | 90 ++++++++++++++++++++++++++++++++++++----------------
yolo/daily-log.jsonl | 1 +
2 files changed, 64 insertions(+), 27 deletions(-)
diff --git a/data/challenges.json b/data/challenges.json
index 4c1aabc..e92c949 100644
--- a/data/challenges.json
+++ b/data/challenges.json
@@ -96656,64 +96656,100 @@
"runs": [
{
"model": "exo__qwen3-30b-a3b-4bit",
- "status": "running",
- "error": null,
- "seconds": null,
+ "status": "error",
+ "error": "timeout after 300s",
+ "seconds": 300,
"cost": null,
"started_at": "2026-09-27T08:27:19.396Z",
- "finished_at": null,
+ "finished_at": "2026-09-27T08:32:19.588Z",
"queued_at": "2026-09-27T08:27:18.845Z",
"fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)"
},
{
"model": "exo__step-3-5-flash-8bit",
- "status": "queued",
- "error": null,
- "seconds": null,
+ "status": "error",
+ "error": "timeout after 300s",
+ "seconds": 300,
"cost": null,
- "started_at": null,
- "finished_at": null,
- "queued_at": "2026-09-27T08:27:18.927Z"
+ "started_at": "2026-09-27T08:32:19.826Z",
+ "finished_at": "2026-09-27T08:37:20.204Z",
+ "queued_at": "2026-09-27T08:27:18.927Z",
+ "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)"
},
{
"model": "exo__glm-4-5-air-8bit",
- "status": "queued",
- "error": null,
- "seconds": null,
+ "status": "error",
+ "error": "timeout after 300s",
+ "seconds": 300,
"cost": null,
- "started_at": null,
- "finished_at": null,
- "queued_at": "2026-09-27T08:27:19.019Z"
+ "started_at": "2026-09-27T08:37:20.322Z",
+ "finished_at": "2026-09-27T08:42:20.644Z",
+ "queued_at": "2026-09-27T08:27:19.019Z",
+ "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)"
},
{
"model": "exo__meta-llama-3-1-8b-instruct-8bit",
- "status": "queued",
- "error": null,
- "seconds": null,
+ "status": "error",
+ "error": "timeout after 300s",
+ "seconds": 300,
"cost": null,
- "started_at": null,
- "finished_at": null,
- "queued_at": "2026-09-27T08:27:19.095Z"
+ "started_at": "2026-09-27T08:42:20.708Z",
+ "finished_at": "2026-09-27T08:47:21.023Z",
+ "queued_at": "2026-09-27T08:27:19.095Z",
+ "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)"
},
{
"model": "exo__gemma-4-e4b-it-8bit",
- "status": "queued",
+ "status": "error",
+ "error": "timeout after 300s",
+ "seconds": 300,
+ "cost": null,
+ "started_at": "2026-09-27T08:47:21.149Z",
+ "finished_at": "2026-09-27T08:52:21.697Z",
+ "queued_at": "2026-09-27T08:27:19.180Z",
+ "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)"
+ },
+ {
+ "model": "exo__qwen3-6-35b-a3b-5bit",
+ "status": "error",
+ "error": "timeout after 300s",
+ "seconds": 300,
+ "cost": null,
+ "started_at": "2026-09-27T08:52:21.753Z",
+ "finished_at": "2026-09-27T08:57:22.034Z",
+ "queued_at": "2026-09-27T08:27:19.297Z",
+ "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)"
+ }
+ ]
+ },
+ {
+ "id": "fcf664ddbe62",
+ "title": "Daily · Decision Tools: Model Comparison Console",
+ "prompt": "Build this as one complete, self-contained HTML file: A side-by-side comparison tool with weighted criteria, editable scores, winner explanation, and shareable summary. Build for a defined audience and primary journey, using realistic content and a strong information hierarchy. Every visible control must work and return clear feedback; include relevant empty, error, and completion states. Make the result cohesive from 390px to 1440px, keyboard accessible with visible focus, and respectful of reduced motion. Use a high-contrast technical visual direction with excellent information density. Success means a first-time user understands the product, completes the core task, and can verify the outcome without instructions.",
+ "category": "Decision Tools",
+ "designTools": false,
+ "created_at": "2026-09-27T09:00:05.394Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "qwen3-14b",
+ "status": "running",
"error": null,
"seconds": null,
"cost": null,
- "started_at": null,
+ "started_at": "2026-09-27T09:00:05.604Z",
"finished_at": null,
- "queued_at": "2026-09-27T08:27:19.180Z"
+ "queued_at": "2026-09-27T09:00:05.475Z"
},
{
- "model": "exo__qwen3-6-35b-a3b-5bit",
+ "model": "qwen25-7b",
"status": "queued",
"error": null,
"seconds": null,
"cost": null,
"started_at": null,
"finished_at": null,
- "queued_at": "2026-09-27T08:27:19.297Z"
+ "queued_at": "2026-09-27T09:00:05.537Z"
}
]
}
diff --git a/yolo/daily-log.jsonl b/yolo/daily-log.jsonl
index bfea509..74bae05 100644
--- a/yolo/daily-log.jsonl
+++ b/yolo/daily-log.jsonl
@@ -880,3 +880,4 @@
{"ts":"2026-09-27T07:11:58.349Z","id":"e5ad69bbb90c","promptId":"kinetic-type","category":"Art","title":"Art Competition #80 — Swarm Typography Poster","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
{"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}
← 6cb07b0 auto-data-snapshot: 2026-09-27T01:29:18 (3 data files) — dat
·
back to Model Arena
·
auto-data-snapshot: 2026-09-27T02:30:26 (3 data files) — dat af97759 →