← back to Model Arena
auto-data-snapshot: 2026-09-26T15:48:33 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl
03609d66f7d712b72e20cd61523784ed36863ef0 · 2026-09-26 15:49:00 -0700 · auto-commit-fleet
Files touched
M data/challenges.jsonM yolo/arena-loop-state.jsonM yolo/daily-log.jsonl
Diff
commit 03609d66f7d712b72e20cd61523784ed36863ef0
Author: auto-commit-fleet <steve@designerwallcoverings.com>
Date: Sat Sep 26 15:49:00 2026 -0700
auto-data-snapshot: 2026-09-26T15:48:33 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl
---
data/challenges.json | 96 +++++++++++++++++++++++++++++++++++++++++-----
yolo/arena-loop-state.json | 2 +-
yolo/daily-log.jsonl | 1 +
3 files changed, 88 insertions(+), 11 deletions(-)
diff --git a/data/challenges.json b/data/challenges.json
index d2cbbf7..dcfb5b6 100644
--- a/data/challenges.json
+++ b/data/challenges.json
@@ -95186,54 +95186,130 @@
},
{
"model": "exo__gpt-oss-20b-mxfp4-q8",
+ "status": "error",
+ "error": "timeout after 300s",
+ "seconds": 300,
+ "cost": null,
+ "started_at": "2026-09-26T22:14:39.221Z",
+ "finished_at": "2026-09-26T22:19:39.562Z",
+ "queued_at": "2026-09-26T22:09:38.778Z",
+ "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)"
+ },
+ {
+ "model": "exo__nvidia-nemotron-3-nano-30b-a3b-mlx-bf16",
+ "status": "error",
+ "error": "timeout after 300s",
+ "seconds": 300,
+ "cost": null,
+ "started_at": "2026-09-26T22:19:39.672Z",
+ "finished_at": "2026-09-26T22:24:39.904Z",
+ "queued_at": "2026-09-26T22:09:38.818Z",
+ "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)"
+ },
+ {
+ "model": "exo__kimi-k2-7-code",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-26T22:24:39.954Z",
+ "finished_at": "2026-09-26T22:24:40.031Z",
+ "queued_at": "2026-09-26T22:09:38.874Z"
+ },
+ {
+ "model": "exo__gemma-4-31b-it-bf16",
+ "status": "error",
+ "error": "timeout after 300s",
+ "seconds": 300,
+ "cost": null,
+ "started_at": "2026-09-26T22:24:40.068Z",
+ "finished_at": "2026-09-26T22:29:40.190Z",
+ "queued_at": "2026-09-26T22:09:38.917Z",
+ "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)"
+ },
+ {
+ "model": "exo__minimax-m2-1-3bit",
+ "status": "error",
+ "error": "timeout after 300s",
+ "seconds": 300,
+ "cost": null,
+ "started_at": "2026-09-26T22:29:40.271Z",
+ "finished_at": "2026-09-26T22:34:40.600Z",
+ "queued_at": "2026-09-26T22:09:38.960Z",
+ "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)"
+ }
+ ]
+ },
+ {
+ "id": "2a1c7d595afa",
+ "title": "Real Work Competition #39 — Lighthouse Focus Timer",
+ "prompt": "Build this as one complete, self-contained HTML file: A focus timer styled as a tiny lighthouse: work sessions sweep the beam and calm the sea, breaks bring gentle waves, a task list is the ships to guide home, and session stats show the night's safe passages. 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": "Real Work",
+ "designTools": false,
+ "created_at": "2026-09-26T22:39:43.893Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "exo__qwen3-5-397b-a17b-6bit",
+ "status": "error",
+ "error": "timeout after 300s",
+ "seconds": 300,
+ "cost": null,
+ "started_at": "2026-09-26T22:39:44.463Z",
+ "finished_at": "2026-09-26T22:44:44.709Z",
+ "queued_at": "2026-09-26T22:39:43.976Z",
+ "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)"
+ },
+ {
+ "model": "exo__qwen3-0-6b-4bit",
"status": "running",
"error": null,
"seconds": null,
"cost": null,
- "started_at": "2026-09-26T22:14:39.221Z",
+ "started_at": "2026-09-26T22:44:44.853Z",
"finished_at": null,
- "queued_at": "2026-09-26T22:09:38.778Z",
+ "queued_at": "2026-09-26T22:39:44.061Z",
"fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)"
},
{
- "model": "exo__nvidia-nemotron-3-nano-30b-a3b-mlx-bf16",
+ "model": "exo__glm-5",
"status": "queued",
"error": null,
"seconds": null,
"cost": null,
"started_at": null,
"finished_at": null,
- "queued_at": "2026-09-26T22:09:38.818Z"
+ "queued_at": "2026-09-26T22:39:44.134Z"
},
{
- "model": "exo__kimi-k2-7-code",
+ "model": "exo__nvidia-nemotron-nano-9b-v2-4bits",
"status": "queued",
"error": null,
"seconds": null,
"cost": null,
"started_at": null,
"finished_at": null,
- "queued_at": "2026-09-26T22:09:38.874Z"
+ "queued_at": "2026-09-26T22:39:44.202Z"
},
{
- "model": "exo__gemma-4-31b-it-bf16",
+ "model": "exo__gemma-4-26b-a4b-it-bf16",
"status": "queued",
"error": null,
"seconds": null,
"cost": null,
"started_at": null,
"finished_at": null,
- "queued_at": "2026-09-26T22:09:38.917Z"
+ "queued_at": "2026-09-26T22:39:44.293Z"
},
{
- "model": "exo__minimax-m2-1-3bit",
+ "model": "exo__meta-llama-3-1-70b-instruct-4bit",
"status": "queued",
"error": null,
"seconds": null,
"cost": null,
"started_at": null,
"finished_at": null,
- "queued_at": "2026-09-26T22:09:38.960Z"
+ "queued_at": "2026-09-26T22:39:44.388Z"
}
]
}
diff --git a/yolo/arena-loop-state.json b/yolo/arena-loop-state.json
index 60fae80..22b0be3 100644
--- a/yolo/arena-loop-state.json
+++ b/yolo/arena-loop-state.json
@@ -1 +1 @@
-{"promptIdx":3,"modelOffset":92,"compCount":{"Art":78,"Culture":77,"News":77,"Political Cartoon":77,"Games":39,"Real Work":38,"Data Viz":38,"Science":38,"Music":38,"Sports":38,"History":38,"Nature & Space":38,"Comedy":38,"Demoscene":38,"Finance":38,"Design":38},"catIdx":5,"perCat":{"Art":1,"Culture":1,"News":1,"Political Cartoon":1,"Games":3,"Real Work":2,"Data Viz":2,"Science":2,"Music":2,"Sports":2,"History":2,"Nature & Space":2,"Comedy":2,"Demoscene":2,"Finance":2,"Design":2}}
\ No newline at end of file
+{"promptIdx":3,"modelOffset":98,"compCount":{"Art":78,"Culture":77,"News":77,"Political Cartoon":77,"Games":39,"Real Work":39,"Data Viz":38,"Science":38,"Music":38,"Sports":38,"History":38,"Nature & Space":38,"Comedy":38,"Demoscene":38,"Finance":38,"Design":38},"catIdx":6,"perCat":{"Art":1,"Culture":1,"News":1,"Political Cartoon":1,"Games":3,"Real Work":3,"Data Viz":2,"Science":2,"Music":2,"Sports":2,"History":2,"Nature & Space":2,"Comedy":2,"Demoscene":2,"Finance":2,"Design":2}}
\ No newline at end of file
diff --git a/yolo/daily-log.jsonl b/yolo/daily-log.jsonl
index 7db277c..5fd158f 100644
--- a/yolo/daily-log.jsonl
+++ b/yolo/daily-log.jsonl
@@ -861,3 +861,4 @@
{"ts":"2026-09-26T20:54:19.016Z","id":"4730e9d0c53d","promptId":"museum","category":"Culture","title":"Culture Competition #77 — Museum of a Lost Civilization","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
{"ts":"2026-09-26T21:29:28.812Z","id":"23d5da4140e7","promptId":"election-viz","category":"News","title":"News Competition #77 — Election Night: Floating Isles","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
{"ts":"2026-09-26T22:04:38.636Z","id":"4513c4b7c7eb","promptId":"editorial-cartoon","category":"Political Cartoon","title":"Political Cartoon Competition #77 — The Seesaw Debate","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-26T22:34:43.804Z","id":"87d3ec7dd134","promptId":"tower","category":"Games","title":"Games Competition #39 — Tower on a Walking Giant","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
← ab8dba9 auto-data-snapshot: 2026-09-26T15:18:06 (3 data files) — dat
·
back to Model Arena
·
auto-data-snapshot: 2026-09-26T16:19:05 (3 data files) — dat aec8cbf →