← back to Model Arena
auto-data-snapshot: 2026-09-18T16:30:11 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl
b73361d95c1e65b1f59867a6b4e50a86a0fa75a4 · 2026-09-18 16:31:33 -0700 · auto-commit-fleet
Files touched
M data/challenges.jsonM yolo/arena-loop-state.jsonM yolo/daily-log.jsonl
Diff
commit b73361d95c1e65b1f59867a6b4e50a86a0fa75a4
Author: auto-commit-fleet <steve@designerwallcoverings.com>
Date: Fri Sep 18 16:31:33 2026 -0700
auto-data-snapshot: 2026-09-18T16:30:11 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl
---
data/challenges.json | 121 +++++++++++++++++++++++++++++++++++++++------
yolo/arena-loop-state.json | 2 +-
yolo/daily-log.jsonl | 2 +
3 files changed, 110 insertions(+), 15 deletions(-)
diff --git a/data/challenges.json b/data/challenges.json
index f5ba8d2..d821dba 100644
--- a/data/challenges.json
+++ b/data/challenges.json
@@ -38373,7 +38373,9 @@
"finished_at": "2026-09-18T22:55:25.311Z",
"queued_at": "2026-09-18T22:55:15.479Z",
"bytes": 748,
- "thumb": true
+ "thumb": true,
+ "aiScore": null,
+ "aiReason": "judge failed: all vision panelists failed"
},
{
"model": "mac1__qwen2-5vl-7b",
@@ -38385,7 +38387,9 @@
"finished_at": "2026-09-18T22:56:03.623Z",
"queued_at": "2026-09-18T22:55:15.492Z",
"bytes": 4788,
- "thumb": true
+ "thumb": true,
+ "aiScore": null,
+ "aiReason": "judge failed: all vision panelists failed"
},
{
"model": "qwen3-14b",
@@ -38397,16 +38401,18 @@
"finished_at": "2026-09-18T22:58:17.475Z",
"queued_at": "2026-09-18T22:55:15.503Z",
"bytes": 6621,
- "thumb": true
+ "thumb": true,
+ "aiScore": null,
+ "aiReason": "judge failed: all vision panelists failed"
},
{
"model": "mlx__qwen3-next-80b-a3b-instruct-4bit",
- "status": "running",
- "error": null,
- "seconds": null,
+ "status": "error",
+ "error": "timeout after 600s",
+ "seconds": 600,
"cost": null,
"started_at": "2026-09-18T22:55:15.540Z",
- "finished_at": null,
+ "finished_at": "2026-09-18T23:05:15.494Z",
"queued_at": "2026-09-18T22:55:15.512Z"
},
{
@@ -38419,18 +38425,105 @@
"finished_at": "2026-09-18T22:58:52.571Z",
"queued_at": "2026-09-18T22:55:15.520Z",
"bytes": 5155,
- "thumb": true
+ "thumb": true,
+ "aiScore": null,
+ "aiReason": "judge failed: all vision panelists failed"
},
{
"model": "mlx__qwen3-30b-a3b-instruct-2507-4bit",
- "status": "queued",
- "error": null,
- "seconds": null,
+ "status": "error",
+ "error": "timeout after 600s",
+ "seconds": 600,
"cost": null,
- "started_at": null,
- "finished_at": null,
+ "started_at": "2026-09-18T23:05:15.501Z",
+ "finished_at": "2026-09-18T23:15:15.501Z",
"queued_at": "2026-09-18T22:55:15.527Z"
}
- ]
+ ],
+ "judging": false,
+ "aiPick": null,
+ "judged_at": "2026-09-18T23:15:15.583Z"
+ },
+ {
+ "id": "a16b7e064eb6",
+ "title": "Nature & Space Competition #1 — Invent Your Own Constellations",
+ "prompt": "Build this as one complete, self-contained HTML file: A night sky where YOU invent the myths: drag between stars to draw your own constellation, name it, and the sky remembers it with a little origin story; hover known INVENTED constellations for lore. 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": "Nature & Space",
+ "designTools": false,
+ "created_at": "2026-09-18T23:20:16.189Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "mlx__qwen3-30b-a3b-instruct-2507-4bit",
+ "status": "error",
+ "error": "timeout after 600s",
+ "seconds": 600,
+ "cost": null,
+ "started_at": "2026-09-18T23:20:16.269Z",
+ "finished_at": "2026-09-18T23:30:16.326Z",
+ "queued_at": "2026-09-18T23:20:16.214Z"
+ },
+ {
+ "model": "exo__qwen3-coder-480b-a35b-instruct-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-18T23:20:16.275Z",
+ "finished_at": "2026-09-18T23:20:16.477Z",
+ "queued_at": "2026-09-18T23:20:16.227Z"
+ },
+ {
+ "model": "mac1__minicpm-v-latest",
+ "status": "done",
+ "error": null,
+ "seconds": 15,
+ "cost": 0,
+ "started_at": "2026-09-18T23:20:16.281Z",
+ "finished_at": "2026-09-18T23:20:31.323Z",
+ "queued_at": "2026-09-18T23:20:16.238Z",
+ "bytes": 2139,
+ "thumb": true,
+ "aiScore": null,
+ "aiReason": "judge failed: all vision panelists failed"
+ },
+ {
+ "model": "exo__qwen3-5-122b-a10b-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-18T23:20:16.490Z",
+ "finished_at": "2026-09-18T23:20:16.818Z",
+ "queued_at": "2026-09-18T23:20:16.247Z"
+ },
+ {
+ "model": "mac1__qwen2-5vl-7b",
+ "status": "done",
+ "error": null,
+ "seconds": 62,
+ "cost": 0,
+ "started_at": "2026-09-18T23:20:31.340Z",
+ "finished_at": "2026-09-18T23:21:33.346Z",
+ "queued_at": "2026-09-18T23:20:16.255Z",
+ "bytes": 7870,
+ "thumb": true,
+ "aiScore": null,
+ "aiReason": "judge failed: all vision panelists failed"
+ },
+ {
+ "model": "exo__gemma-4-26b-a4b-it-6bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-18T23:20:16.841Z",
+ "finished_at": "2026-09-18T23:20:16.958Z",
+ "queued_at": "2026-09-18T23:20:16.263Z"
+ }
+ ],
+ "judging": false,
+ "aiPick": null,
+ "judged_at": "2026-09-18T23:30:17.700Z"
}
]
\ No newline at end of file
diff --git a/yolo/arena-loop-state.json b/yolo/arena-loop-state.json
index cb4269f..822b605 100644
--- a/yolo/arena-loop-state.json
+++ b/yolo/arena-loop-state.json
@@ -1 +1 @@
-{"promptIdx":3,"modelOffset":4,"compCount":{"Art":2,"Culture":1,"News":1,"Political Cartoon":1,"Games":1,"Real Work":1,"Data Viz":1,"Science":1,"Music":1,"Sports":1,"History":1},"catIdx":11,"perCat":{"Art":1,"Culture":1,"News":1,"Political Cartoon":1,"Games":1,"Real Work":1,"Data Viz":1,"Science":1,"Music":1,"Sports":1,"History":1}}
\ No newline at end of file
+{"promptIdx":3,"modelOffset":10,"compCount":{"Art":2,"Culture":1,"News":1,"Political Cartoon":1,"Games":1,"Real Work":1,"Data Viz":1,"Science":1,"Music":1,"Sports":1,"History":1,"Nature & Space":1},"catIdx":12,"perCat":{"Art":1,"Culture":1,"News":1,"Political Cartoon":1,"Games":1,"Real Work":1,"Data Viz":1,"Science":1,"Music":1,"Sports":1,"History":1,"Nature & Space":1}}
\ No newline at end of file
diff --git a/yolo/daily-log.jsonl b/yolo/daily-log.jsonl
index b90a194..e71e3c4 100644
--- a/yolo/daily-log.jsonl
+++ b/yolo/daily-log.jsonl
@@ -64,3 +64,5 @@
{"ts":"2026-09-18T22:39:52.925Z","id":"b39dc5aa742d","promptId":"solar","category":"Science","title":"Science Competition #1 — Conduct the Solar System","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
{"ts":"2026-09-18T22:45:01.239Z","id":"ea9bc427c464","promptId":"sequencer","category":"Music","title":"Music Competition #1 — Constellation Sequencer","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
{"ts":"2026-09-18T22:50:09.439Z","id":"d6e573770d85","promptId":"standings","category":"Sports","title":"Sports Competition #1 — Zero-G Relay League","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-18T23:15:16.039Z","id":"9deb53d2058b","promptId":"timeline-hist","category":"History","title":"History Competition #1 — Walk-Through Age of Invention","models":6,"done":4,"errored":2,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-18T23:30:16.598Z","id":"a16b7e064eb6","promptId":"starmap","category":"Nature & Space","title":"Nature & Space Competition #1 — Invent Your Own Constellations","models":6,"done":2,"errored":4,"settled":true,"aiPick":null,"loop":true}
← 08d0650 auto-data-snapshot: 2026-09-18T15:58:14 (3 data files) — dat
·
back to Model Arena
·
auto-data-snapshot: 2026-09-18T17:02:10 (3 data files) — dat af1a690 →