← back to Model Arena
auto-data-snapshot: 2026-09-27T10:46:12 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl
3520c4f280f423912dbcb9c1af75299904ec0bcd · 2026-09-27 10:46:49 -0700 · auto-commit-fleet
Files touched
M data/challenges.jsonM yolo/arena-loop-state.jsonM yolo/daily-log.jsonl
Diff
commit 3520c4f280f423912dbcb9c1af75299904ec0bcd
Author: auto-commit-fleet <steve@designerwallcoverings.com>
Date: Sun Sep 27 10:46:49 2026 -0700
auto-data-snapshot: 2026-09-27T10:46:12 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl
---
data/challenges.json | 147 +++++++++++++++++++++++++++++++++------------
yolo/arena-loop-state.json | 2 +-
yolo/daily-log.jsonl | 1 +
3 files changed, 111 insertions(+), 39 deletions(-)
diff --git a/data/challenges.json b/data/challenges.json
index a6e6433..f04bd97 100644
--- a/data/challenges.json
+++ b/data/challenges.json
@@ -97871,66 +97871,66 @@
"runs": [
{
"model": "exo__gemma-4-e4b-it-6bit",
- "status": "error",
- "error": "never started — model host busy/down",
+ "status": "queued",
+ "error": null,
"seconds": 0,
"cost": null,
"started_at": null,
- "finished_at": "2026-09-27T16:35:02.989Z",
- "queued_at": "2026-09-27T15:49:45.444Z",
+ "finished_at": null,
+ "queued_at": "2026-09-27T17:23:10.326Z",
"fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3-30B-A3B-Instruct-2507-4bit)"
},
{
"model": "exo__nvidia-nemotron-3-nano-30b-a3b-mlx-5bit",
- "status": "error",
- "error": "timeout after 300s",
+ "status": "queued",
+ "error": null,
"seconds": 300,
"cost": null,
- "started_at": "2026-09-27T15:49:41.681Z",
- "finished_at": "2026-09-27T15:54:42.132Z",
- "queued_at": "2026-09-27T15:44:41.071Z",
+ "started_at": null,
+ "finished_at": null,
+ "queued_at": "2026-09-27T17:23:10.463Z",
"fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3-30B-A3B-Instruct-2507-4bit)"
},
{
"model": "exo__glm-4-7-flash-6bit",
- "status": "error",
- "error": "timeout after 300s",
+ "status": "queued",
+ "error": null,
"seconds": 300,
"cost": null,
- "started_at": "2026-09-27T15:54:42.195Z",
- "finished_at": "2026-09-27T15:59:42.420Z",
- "queued_at": "2026-09-27T15:44:41.115Z",
+ "started_at": null,
+ "finished_at": null,
+ "queued_at": "2026-09-27T17:23:10.589Z",
"fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3-30B-A3B-Instruct-2507-4bit)"
},
{
"model": "exo__qwen3-5-35b-a3b-8bit",
- "status": "error",
- "error": "timed out (watchdog) — model host unresponsive",
+ "status": "queued",
+ "error": null,
"seconds": null,
"cost": null,
- "started_at": "2026-09-27T15:59:44.951Z",
- "finished_at": "2026-09-27T16:11:02.930Z",
- "queued_at": "2026-09-27T15:44:41.153Z"
+ "started_at": null,
+ "finished_at": null,
+ "queued_at": "2026-09-27T17:23:10.748Z"
},
{
"model": "exo__glm-4-7-8bit-gs32",
- "status": "error",
- "error": "never started — model host busy/down",
+ "status": "queued",
+ "error": null,
"seconds": 0,
"cost": null,
"started_at": null,
- "finished_at": "2026-09-27T16:30:02.967Z",
- "queued_at": "2026-09-27T15:44:41.211Z"
+ "finished_at": null,
+ "queued_at": "2026-09-27T17:23:10.904Z"
},
{
"model": "exo__glm-5-1",
- "status": "error",
- "error": "never started — model host busy/down",
+ "status": "queued",
+ "error": null,
"seconds": 0,
"cost": null,
"started_at": null,
- "finished_at": "2026-09-27T16:30:02.967Z",
- "queued_at": "2026-09-27T15:44:41.269Z"
+ "finished_at": null,
+ "queued_at": "2026-09-27T17:23:11.043Z"
}
]
},
@@ -97945,63 +97945,134 @@
"runs": [
{
"model": "exo__kimi-k2-5",
+ "status": "error",
+ "error": "never started — model host busy/down",
+ "seconds": 0,
+ "cost": null,
+ "started_at": null,
+ "finished_at": "2026-09-27T17:20:03.333Z",
+ "queued_at": "2026-09-27T16:34:42.946Z"
+ },
+ {
+ "model": "exo__qwen3-5-397b-a17b-8bit",
+ "status": "error",
+ "error": "never started — model host busy/down",
+ "seconds": 0,
+ "cost": null,
+ "started_at": null,
+ "finished_at": "2026-09-27T17:20:03.334Z",
+ "queued_at": "2026-09-27T16:34:43.029Z"
+ },
+ {
+ "model": "exo__minimax-m2-7-5bit",
+ "status": "error",
+ "error": "never started — model host busy/down",
+ "seconds": 0,
+ "cost": null,
+ "started_at": null,
+ "finished_at": "2026-09-27T17:20:03.334Z",
+ "queued_at": "2026-09-27T16:34:43.120Z"
+ },
+ {
+ "model": "exo__qwen3-5-2b-mlx-8bit",
+ "status": "error",
+ "error": "never started — model host busy/down",
+ "seconds": 0,
+ "cost": null,
+ "started_at": null,
+ "finished_at": "2026-09-27T17:20:03.334Z",
+ "queued_at": "2026-09-27T16:34:43.208Z"
+ },
+ {
+ "model": "exo__deepseek-v3-2-8bit",
+ "status": "error",
+ "error": "never started — model host busy/down",
+ "seconds": 0,
+ "cost": null,
+ "started_at": null,
+ "finished_at": "2026-09-27T17:20:03.349Z",
+ "queued_at": "2026-09-27T16:34:43.281Z"
+ },
+ {
+ "model": "exo__qwen3-5-27b-4bit",
+ "status": "error",
+ "error": "never started — model host busy/down",
+ "seconds": 0,
+ "cost": null,
+ "started_at": null,
+ "finished_at": "2026-09-27T17:20:03.349Z",
+ "queued_at": "2026-09-27T16:34:43.361Z"
+ }
+ ]
+ },
+ {
+ "id": "735f961ecedb",
+ "title": "Art Competition #82 — Living Ink Canvas",
+ "prompt": "Build this as one complete, self-contained HTML file: A generative 'living ink' canvas where cursor speed is brush pressure: fast strokes splatter, slow strokes bloom into calligraphic petals. The palette drifts with an imagined time-of-day, and one keypress freezes the piece into a framed 'gallery print' with an invented placard. 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": "Art",
+ "designTools": false,
+ "created_at": "2026-09-27T17:24:50.831Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "exo__gemma-4-e2b-it-8bit",
"status": "queued",
"error": null,
"seconds": null,
"cost": null,
"started_at": null,
"finished_at": null,
- "queued_at": "2026-09-27T16:34:42.946Z"
+ "queued_at": "2026-09-27T17:24:50.898Z"
},
{
- "model": "exo__qwen3-5-397b-a17b-8bit",
+ "model": "exo__qwen3-coder-next-5bit",
"status": "queued",
"error": null,
"seconds": null,
"cost": null,
"started_at": null,
"finished_at": null,
- "queued_at": "2026-09-27T16:34:43.029Z"
+ "queued_at": "2026-09-27T17:24:50.953Z"
},
{
- "model": "exo__minimax-m2-7-5bit",
+ "model": "exo__glm-4-7-flash-4bit",
"status": "queued",
"error": null,
"seconds": null,
"cost": null,
"started_at": null,
"finished_at": null,
- "queued_at": "2026-09-27T16:34:43.120Z"
+ "queued_at": "2026-09-27T17:24:51.003Z"
},
{
- "model": "exo__qwen3-5-2b-mlx-8bit",
+ "model": "exo__qwen3-6-35b-a3b-8bit",
"status": "queued",
"error": null,
"seconds": null,
"cost": null,
"started_at": null,
"finished_at": null,
- "queued_at": "2026-09-27T16:34:43.208Z"
+ "queued_at": "2026-09-27T17:24:51.060Z"
},
{
- "model": "exo__deepseek-v3-2-8bit",
+ "model": "exo__qwen3-5-9b-4bit",
"status": "queued",
"error": null,
"seconds": null,
"cost": null,
"started_at": null,
"finished_at": null,
- "queued_at": "2026-09-27T16:34:43.281Z"
+ "queued_at": "2026-09-27T17:24:51.121Z"
},
{
- "model": "exo__qwen3-5-27b-4bit",
+ "model": "exo__qwen3-235b-a22b-instruct-2507-8bit",
"status": "queued",
"error": null,
"seconds": null,
"cost": null,
"started_at": null,
"finished_at": null,
- "queued_at": "2026-09-27T16:34:43.361Z"
+ "queued_at": "2026-09-27T17:24:51.182Z"
}
]
}
diff --git a/yolo/arena-loop-state.json b/yolo/arena-loop-state.json
index e047d11..049e9ab 100644
--- a/yolo/arena-loop-state.json
+++ b/yolo/arena-loop-state.json
@@ -1 +1 @@
-{"promptIdx":3,"modelOffset":40,"compCount":{"Art":81,"Culture":80,"News":80,"Political Cartoon":80,"Games":40,"Real Work":40,"Data Viz":40,"Science":40,"Music":40,"Sports":40,"History":40,"Nature & Space":40,"Comedy":40,"Demoscene":40,"Finance":40,"Design":40},"catIdx":0,"perCat":{"Art":4,"Culture":4,"News":4,"Political Cartoon":4,"Games":1,"Real Work":1,"Data Viz":1,"Science":1,"Music":1,"Sports":1,"History":1,"Nature & Space":1,"Comedy":1,"Demoscene":1,"Finance":1,"Design":1}}
\ No newline at end of file
+{"promptIdx":3,"modelOffset":46,"compCount":{"Art":82,"Culture":80,"News":80,"Political Cartoon":80,"Games":40,"Real Work":40,"Data Viz":40,"Science":40,"Music":40,"Sports":40,"History":40,"Nature & Space":40,"Comedy":40,"Demoscene":40,"Finance":40,"Design":40},"catIdx":1,"perCat":{"Art":1,"Culture":4,"News":4,"Political Cartoon":4,"Games":1,"Real Work":1,"Data Viz":1,"Science":1,"Music":1,"Sports":1,"History":1,"Nature & Space":1,"Comedy":1,"Demoscene":1,"Finance":1,"Design":1}}
\ No newline at end of file
diff --git a/yolo/daily-log.jsonl b/yolo/daily-log.jsonl
index d5dd0e6..25ee3c3 100644
--- a/yolo/daily-log.jsonl
+++ b/yolo/daily-log.jsonl
@@ -895,3 +895,4 @@
{"ts":"2026-09-27T14:38:59.940Z","id":"6aa278ada14d","promptId":"portfolio","category":"Finance","title":"Finance Competition #40 — Galactic Exchange Portfolio","models":6,"done":2,"errored":4,"settled":true,"aiPick":null,"loop":true}
{"ts":"2026-09-27T15:09:08.489Z","id":"7ca928b659b7","promptId":"components","category":"Design","title":"Design Competition #40 — Design System Safari","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
{"ts":"2026-09-27T16:29:42.824Z","id":"5faec93e5a39","promptId":"climate-story","category":"News","title":"News Competition #80 — The City That Floods As You Scroll","models":6,"done":0,"errored":3,"settled":false,"aiPick":null,"loop":true}
+{"ts":"2026-09-27T17:19:50.709Z","id":"f599ddf5c0be","promptId":"civic-explainer","category":"Political Cartoon","title":"Political Cartoon Competition #80 — How a Law Gets Passed (Rube Goldberg)","models":6,"done":0,"errored":0,"settled":false,"aiPick":null,"loop":true}
← f615d20 auto-data-snapshot: 2026-09-27T09:45:05 (3 data files) — dat
·
back to Model Arena
·
auto-data-snapshot: 2026-09-27T11:16:55 (3 data files) — dat c169ae8 →