← back to Model Arena
auto-data-snapshot: 2026-09-27T14:51:41 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl
48cf36d1a2317e812f7dba2877c6e11e4cda01fa · 2026-09-27 14:52:08 -0700 · auto-commit-fleet
Files touched
M data/challenges.jsonM yolo/arena-loop-state.jsonM yolo/daily-log.jsonl
Diff
commit 48cf36d1a2317e812f7dba2877c6e11e4cda01fa
Author: auto-commit-fleet <steve@designerwallcoverings.com>
Date: Sun Sep 27 14:52:08 2026 -0700
auto-data-snapshot: 2026-09-27T14:51:41 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl
---
data/challenges.json | 93 ++++++++++++++++++++++++++++++++++++++++------
yolo/arena-loop-state.json | 2 +-
yolo/daily-log.jsonl | 1 +
3 files changed, 84 insertions(+), 12 deletions(-)
diff --git a/data/challenges.json b/data/challenges.json
index b2a05ba..6b873fc 100644
--- a/data/challenges.json
+++ b/data/challenges.json
@@ -98300,63 +98300,134 @@
"runs": [
{
"model": "exo__gemma-4-e4b-it-4bit",
+ "status": "error",
+ "error": "never started — model host busy/down",
+ "seconds": 0,
+ "cost": null,
+ "started_at": null,
+ "finished_at": "2026-09-27T21:30:35.585Z",
+ "queued_at": "2026-09-27T20:45:16.486Z"
+ },
+ {
+ "model": "exo__step-3-5-flash-4bit",
+ "status": "error",
+ "error": "never started — model host busy/down",
+ "seconds": 0,
+ "cost": null,
+ "started_at": null,
+ "finished_at": "2026-09-27T21:30:35.594Z",
+ "queued_at": "2026-09-27T20:45:16.648Z"
+ },
+ {
+ "model": "exo__minimax-m2-5-4bit",
+ "status": "error",
+ "error": "never started — model host busy/down",
+ "seconds": 0,
+ "cost": null,
+ "started_at": null,
+ "finished_at": "2026-09-27T21:30:35.594Z",
+ "queued_at": "2026-09-27T20:45:16.727Z"
+ },
+ {
+ "model": "exo__gemma-4-26b-a4b-it-8bit",
+ "status": "error",
+ "error": "never started — model host busy/down",
+ "seconds": 0,
+ "cost": null,
+ "started_at": null,
+ "finished_at": "2026-09-27T21:30:35.594Z",
+ "queued_at": "2026-09-27T20:45:16.825Z"
+ },
+ {
+ "model": "exo__llama-3-2-3b-instruct-4bit",
+ "status": "error",
+ "error": "never started — model host busy/down",
+ "seconds": 0,
+ "cost": null,
+ "started_at": null,
+ "finished_at": "2026-09-27T21:30:35.594Z",
+ "queued_at": "2026-09-27T20:45:17.008Z"
+ },
+ {
+ "model": "exo__qwen3-30b-a3b-4bit",
+ "status": "error",
+ "error": "never started — model host busy/down",
+ "seconds": 0,
+ "cost": null,
+ "started_at": null,
+ "finished_at": "2026-09-27T21:30:35.594Z",
+ "queued_at": "2026-09-27T20:45:17.082Z"
+ }
+ ]
+ },
+ {
+ "id": "b10815ca1fd7",
+ "title": "Real Work Competition #41 — Timesheet Garden",
+ "prompt": "Build this as one complete, self-contained HTML file: A timesheet that grows your week as a garden — each logged hour sprouts a plant in the right plot, overtime wilts, and an 'invoice' view harvests it into a clean printable total with rate math and validation. 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": "2026-09-27T21:35:23.571Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "exo__step-3-5-flash-8bit",
"status": "queued",
"error": null,
"seconds": null,
"cost": null,
"started_at": null,
"finished_at": null,
- "queued_at": "2026-09-27T20:45:16.486Z"
+ "queued_at": "2026-09-27T21:35:23.699Z"
},
{
- "model": "exo__step-3-5-flash-4bit",
+ "model": "exo__glm-4-5-air-8bit",
"status": "queued",
"error": null,
"seconds": null,
"cost": null,
"started_at": null,
"finished_at": null,
- "queued_at": "2026-09-27T20:45:16.648Z"
+ "queued_at": "2026-09-27T21:35:23.810Z"
},
{
- "model": "exo__minimax-m2-5-4bit",
+ "model": "exo__meta-llama-3-1-8b-instruct-8bit",
"status": "queued",
"error": null,
"seconds": null,
"cost": null,
"started_at": null,
"finished_at": null,
- "queued_at": "2026-09-27T20:45:16.727Z"
+ "queued_at": "2026-09-27T21:35:23.908Z"
},
{
- "model": "exo__gemma-4-26b-a4b-it-8bit",
+ "model": "exo__gemma-4-e4b-it-8bit",
"status": "queued",
"error": null,
"seconds": null,
"cost": null,
"started_at": null,
"finished_at": null,
- "queued_at": "2026-09-27T20:45:16.825Z"
+ "queued_at": "2026-09-27T21:35:24.038Z"
},
{
- "model": "exo__llama-3-2-3b-instruct-4bit",
+ "model": "exo__qwen3-6-35b-a3b-5bit",
"status": "queued",
"error": null,
"seconds": null,
"cost": null,
"started_at": null,
"finished_at": null,
- "queued_at": "2026-09-27T20:45:17.008Z"
+ "queued_at": "2026-09-27T21:35:24.130Z"
},
{
- "model": "exo__qwen3-30b-a3b-4bit",
+ "model": "exo__llama-3-2-1b-instruct-4bit",
"status": "queued",
"error": null,
"seconds": null,
"cost": null,
"started_at": null,
"finished_at": null,
- "queued_at": "2026-09-27T20:45:17.082Z"
+ "queued_at": "2026-09-27T21:35:24.182Z"
}
]
}
diff --git a/yolo/arena-loop-state.json b/yolo/arena-loop-state.json
index 403177b..f06f1db 100644
--- a/yolo/arena-loop-state.json
+++ b/yolo/arena-loop-state.json
@@ -1 +1 @@
-{"promptIdx":3,"modelOffset":70,"compCount":{"Art":82,"Culture":81,"News":81,"Political Cartoon":81,"Games":41,"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":5,"perCat":{"Art":1,"Culture":1,"News":1,"Political Cartoon":1,"Games":2,"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":76,"compCount":{"Art":82,"Culture":81,"News":81,"Political Cartoon":81,"Games":41,"Real Work":41,"Data Viz":40,"Science":40,"Music":40,"Sports":40,"History":40,"Nature & Space":40,"Comedy":40,"Demoscene":40,"Finance":40,"Design":40},"catIdx":6,"perCat":{"Art":1,"Culture":1,"News":1,"Political Cartoon":1,"Games":2,"Real Work":2,"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 e8ee01c..6cdf64f 100644
--- a/yolo/daily-log.jsonl
+++ b/yolo/daily-log.jsonl
@@ -900,3 +900,4 @@
{"ts":"2026-09-27T19:00:03.487Z","id":"6f8f28759c7c","promptId":"museum","category":"Culture","title":"Culture Competition #81 — Museum of a Lost Civilization","models":6,"done":0,"errored":0,"settled":false,"aiPick":null,"loop":true}
{"ts":"2026-09-27T19:50:09.384Z","id":"8c356f04030a","promptId":"election-viz","category":"News","title":"News Competition #81 — Election Night: Floating Isles","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
{"ts":"2026-09-27T20:40:16.255Z","id":"4340f4c0ccb8","promptId":"editorial-cartoon","category":"Political Cartoon","title":"Political Cartoon Competition #81 — The Seesaw Debate","models":6,"done":0,"errored":0,"settled":false,"aiPick":null,"loop":true}
+{"ts":"2026-09-27T21:30:23.433Z","id":"175942714cfe","promptId":"breakout","category":"Games","title":"Games Competition #41 — Wake the Dragon Breakout","models":6,"done":0,"errored":0,"settled":false,"aiPick":null,"loop":true}
← 2ebb3e0 auto-data-snapshot: 2026-09-27T13:50:24 (3 data files) — dat
·
back to Model Arena
·
auto-data-snapshot: 2026-09-27T15:22:13 (2 data files) — dat 9ab7a9c →