← back to Model Arena
auto-data-snapshot: 2026-09-26T16:49:35 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl
1ce5d844b17ffd4bfd614ac24accc323d3861dc2 · 2026-09-26 16:50:18 -0700 · auto-commit-fleet
Files touched
M data/challenges.jsonM yolo/arena-loop-state.jsonM yolo/daily-log.jsonl
Diff
commit 1ce5d844b17ffd4bfd614ac24accc323d3861dc2
Author: auto-commit-fleet <steve@designerwallcoverings.com>
Date: Sat Sep 26 16:50:18 2026 -0700
auto-data-snapshot: 2026-09-26T16:49:35 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl
---
data/challenges.json | 101 +++++++++++++++++++++++++++++++++++++++------
yolo/arena-loop-state.json | 2 +-
yolo/daily-log.jsonl | 1 +
3 files changed, 91 insertions(+), 13 deletions(-)
diff --git a/data/challenges.json b/data/challenges.json
index 5501bfd..2e9ae7a 100644
--- a/data/challenges.json
+++ b/data/challenges.json
@@ -95328,64 +95328,141 @@
"runs": [
{
"model": "exo__qwen3-5-35b-a3b-4bit",
+ "status": "error",
+ "error": "timeout after 300s",
+ "seconds": 300,
+ "cost": null,
+ "started_at": "2026-09-26T23:14:54.478Z",
+ "finished_at": "2026-09-26T23:19:54.641Z",
+ "queued_at": "2026-09-26T23:14:54.176Z",
+ "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)"
+ },
+ {
+ "model": "exo__minimax-m2-1-8bit",
+ "status": "error",
+ "error": "timeout after 300s",
+ "seconds": 300,
+ "cost": null,
+ "started_at": "2026-09-26T23:19:54.711Z",
+ "finished_at": "2026-09-26T23:24:54.833Z",
+ "queued_at": "2026-09-26T23:14:54.230Z",
+ "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)"
+ },
+ {
+ "model": "exo__gemma-4-e2b-it-6bit",
+ "status": "error",
+ "error": "timeout after 300s",
+ "seconds": 300,
+ "cost": null,
+ "started_at": "2026-09-26T23:24:54.871Z",
+ "finished_at": "2026-09-26T23:29:55.007Z",
+ "queued_at": "2026-09-26T23:14:54.286Z",
+ "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)"
+ },
+ {
+ "model": "exo__qwen3-5-27b-8bit",
+ "status": "error",
+ "error": "timeout after 300s",
+ "seconds": 300,
+ "cost": null,
+ "started_at": "2026-09-26T23:29:55.070Z",
+ "finished_at": "2026-09-26T23:34:55.242Z",
+ "queued_at": "2026-09-26T23:14:54.333Z",
+ "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)"
+ },
+ {
+ "model": "exo__kimi-k2-thinking",
+ "status": "error",
+ "error": "timeout after 300s",
+ "seconds": 300,
+ "cost": null,
+ "started_at": "2026-09-26T23:34:55.273Z",
+ "finished_at": "2026-09-26T23:39:55.388Z",
+ "queued_at": "2026-09-26T23:14:54.373Z",
+ "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)"
+ },
+ {
+ "model": "exo__qwen3-coder-next-bf16",
+ "status": "error",
+ "error": "timeout after 300s",
+ "seconds": 300,
+ "cost": null,
+ "started_at": "2026-09-26T23:39:55.425Z",
+ "finished_at": "2026-09-26T23:44:55.571Z",
+ "queued_at": "2026-09-26T23:14:54.415Z",
+ "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)"
+ }
+ ]
+ },
+ {
+ "id": "77bf27d22094",
+ "title": "Science Competition #39 — Cell as a Factory-City",
+ "prompt": "Build this as one complete, self-contained HTML file: A cell explainer as a bustling factory-city (SVG): click organelles to read their 'job posting' and watch a glucose delivery truck route through the city to make ATP, with a guided tour and a quiz-yourself mode. 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": "Science",
+ "designTools": false,
+ "created_at": "2026-09-26T23:49:56.415Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "exo__deepseek-v3-2-4bit",
"status": "running",
"error": null,
"seconds": null,
"cost": null,
- "started_at": "2026-09-26T23:14:54.478Z",
+ "started_at": "2026-09-26T23:49:56.809Z",
"finished_at": null,
- "queued_at": "2026-09-26T23:14:54.176Z",
+ "queued_at": "2026-09-26T23:49:56.470Z",
"fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)"
},
{
- "model": "exo__minimax-m2-1-8bit",
+ "model": "exo__nvidia-nemotron-nano-9b-v2-6bit",
"status": "queued",
"error": null,
"seconds": null,
"cost": null,
"started_at": null,
"finished_at": null,
- "queued_at": "2026-09-26T23:14:54.230Z"
+ "queued_at": "2026-09-26T23:49:56.521Z"
},
{
- "model": "exo__gemma-4-e2b-it-6bit",
+ "model": "exo__meta-llama-3-1-8b-instruct-bf16",
"status": "queued",
"error": null,
"seconds": null,
"cost": null,
"started_at": null,
"finished_at": null,
- "queued_at": "2026-09-26T23:14:54.286Z"
+ "queued_at": "2026-09-26T23:49:56.571Z"
},
{
- "model": "exo__qwen3-5-27b-8bit",
+ "model": "exo__gemma-4-e4b-it-bf16",
"status": "queued",
"error": null,
"seconds": null,
"cost": null,
"started_at": null,
"finished_at": null,
- "queued_at": "2026-09-26T23:14:54.333Z"
+ "queued_at": "2026-09-26T23:49:56.619Z"
},
{
- "model": "exo__kimi-k2-thinking",
+ "model": "exo__qwen3-5-397b-a17b-4bit",
"status": "queued",
"error": null,
"seconds": null,
"cost": null,
"started_at": null,
"finished_at": null,
- "queued_at": "2026-09-26T23:14:54.373Z"
+ "queued_at": "2026-09-26T23:49:56.677Z"
},
{
- "model": "exo__qwen3-coder-next-bf16",
+ "model": "exo__glm-4-5-air-bf16",
"status": "queued",
"error": null,
"seconds": null,
"cost": null,
"started_at": null,
"finished_at": null,
- "queued_at": "2026-09-26T23:14:54.415Z"
+ "queued_at": "2026-09-26T23:49:56.734Z"
}
]
}
diff --git a/yolo/arena-loop-state.json b/yolo/arena-loop-state.json
index d16f8d4..78ad459 100644
--- a/yolo/arena-loop-state.json
+++ b/yolo/arena-loop-state.json
@@ -1 +1 @@
-{"promptIdx":3,"modelOffset":104,"compCount":{"Art":78,"Culture":77,"News":77,"Political Cartoon":77,"Games":39,"Real Work":39,"Data Viz":39,"Science":38,"Music":38,"Sports":38,"History":38,"Nature & Space":38,"Comedy":38,"Demoscene":38,"Finance":38,"Design":38},"catIdx":7,"perCat":{"Art":1,"Culture":1,"News":1,"Political Cartoon":1,"Games":3,"Real Work":3,"Data Viz":3,"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":110,"compCount":{"Art":78,"Culture":77,"News":77,"Political Cartoon":77,"Games":39,"Real Work":39,"Data Viz":39,"Science":39,"Music":38,"Sports":38,"History":38,"Nature & Space":38,"Comedy":38,"Demoscene":38,"Finance":38,"Design":38},"catIdx":8,"perCat":{"Art":1,"Culture":1,"News":1,"Political Cartoon":1,"Games":3,"Real Work":3,"Data Viz":3,"Science":3,"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 2adae9a..3a1b3c7 100644
--- a/yolo/daily-log.jsonl
+++ b/yolo/daily-log.jsonl
@@ -863,3 +863,4 @@
{"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}
{"ts":"2026-09-26T23:09:54.056Z","id":"2a1c7d595afa","promptId":"pomodoro","category":"Real Work","title":"Real Work Competition #39 — Lighthouse Focus Timer","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-26T23:44:56.359Z","id":"850b8b67e16f","promptId":"scatter","category":"Data Viz","title":"Data Viz Competition #39 — Planet Dating Show","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
← aec8cbf auto-data-snapshot: 2026-09-26T16:19:05 (3 data files) — dat
·
back to Model Arena
·
auto-data-snapshot: 2026-09-26T17:20:23 (2 data files) — dat cdd90c5 →