← back to Model Arena
auto-data-snapshot: 2026-09-27T22:40:22 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl
7639ad721db5e359f5f3f53ea0032bbde5902831 · 2026-09-27 22:40:56 -0700 · auto-commit-fleet
Files touched
M data/challenges.jsonM yolo/arena-loop-state.jsonM yolo/daily-log.jsonl
Diff
commit 7639ad721db5e359f5f3f53ea0032bbde5902831
Author: auto-commit-fleet <steve@designerwallcoverings.com>
Date: Sun Sep 27 22:40:56 2026 -0700
auto-data-snapshot: 2026-09-27T22:40:22 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl
---
data/challenges.json | 114 ++++++++++++++++++++++++++++++++++++++++-----
yolo/arena-loop-state.json | 2 +-
yolo/daily-log.jsonl | 2 +
3 files changed, 105 insertions(+), 13 deletions(-)
diff --git a/data/challenges.json b/data/challenges.json
index ac1bc82..b9f3033 100644
--- a/data/challenges.json
+++ b/data/challenges.json
@@ -99427,7 +99427,9 @@
"finished_at": "2026-09-28T05:05:26.034Z",
"queued_at": "2026-09-28T05:04:55.622Z",
"bytes": 3786,
- "thumb": true
+ "thumb": true,
+ "aiScore": null,
+ "aiReason": "judge failed: all vision panelists failed"
},
{
"model": "mlx__qwen3-30b-a3b-instruct-2507-4bit",
@@ -99461,29 +99463,117 @@
"finished_at": "2026-09-28T05:05:39.074Z",
"queued_at": "2026-09-28T05:04:55.865Z",
"bytes": 757,
- "thumb": true
+ "thumb": true,
+ "aiScore": null,
+ "aiReason": "judge failed: all vision panelists failed"
},
{
"model": "mlx__qwen3-8-27b-8bit",
- "status": "running",
- "error": null,
- "seconds": null,
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 300,
"cost": null,
"started_at": "2026-09-28T05:09:56.465Z",
- "finished_at": null,
- "queued_at": "2026-09-28T05:04:55.947Z"
+ "finished_at": "2026-09-28T05:14:56.710Z",
+ "queued_at": "2026-09-28T05:04:55.947Z",
+ "fellBack": "http://127.0.0.1:52415 (mlx-community/MiniMax-M2.7-4bit)"
},
{
"model": "exo__qwen3-5-122b-a10b-4bit",
- "status": "running",
- "error": null,
- "seconds": null,
+ "status": "error",
+ "error": "timeout after 300s",
+ "seconds": 300,
"cost": null,
"started_at": "2026-09-28T05:09:57.087Z",
- "finished_at": null,
+ "finished_at": "2026-09-28T05:14:57.395Z",
"queued_at": "2026-09-28T05:04:56.017Z",
"fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3-Next-80B-A3B-Instruct-4bit)"
}
- ]
+ ],
+ "judging": false,
+ "aiPick": null,
+ "judged_at": "2026-09-28T05:14:57.814Z"
+ },
+ {
+ "id": "85093a3aecdd",
+ "title": "Art Competition #84 — Swarm Typography Poster",
+ "prompt": "Build this as one complete, self-contained HTML file: A kinetic-type poster for an INVENTED avant-garde festival where the headline letters behave like a flocking swarm — scattering from the cursor and re-forming the title — with a slider that morphs the mood from 'whisper' to 'scream'. 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": "2026-09-28T05:20:05.072Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "mac1__qwen2-5vl-7b",
+ "status": "done",
+ "error": null,
+ "seconds": 32,
+ "cost": 0,
+ "started_at": "2026-09-28T05:20:05.326Z",
+ "finished_at": "2026-09-28T05:20:37.014Z",
+ "queued_at": "2026-09-28T05:20:05.107Z",
+ "bytes": 3576,
+ "thumb": true,
+ "aiScore": null,
+ "aiReason": "judge failed: all vision panelists failed"
+ },
+ {
+ "model": "mlx__mlx-community-qwen3-30b-a3b-instruct-2507-4bit",
+ "status": "error",
+ "error": "timeout after 300s",
+ "seconds": 300,
+ "cost": null,
+ "started_at": "2026-09-28T05:20:05.364Z",
+ "finished_at": "2026-09-28T05:25:05.462Z",
+ "queued_at": "2026-09-28T05:20:05.142Z"
+ },
+ {
+ "model": "exo__gemma-4-26b-a4b-it-6bit",
+ "status": "error",
+ "error": "timeout after 300s",
+ "seconds": 300,
+ "cost": null,
+ "started_at": "2026-09-28T05:20:05.400Z",
+ "finished_at": "2026-09-28T05:25:05.533Z",
+ "queued_at": "2026-09-28T05:20:05.188Z",
+ "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3-Next-80B-A3B-Instruct-4bit)"
+ },
+ {
+ "model": "exo__qwen3-6-35b-a3b-bf16",
+ "status": "error",
+ "error": "timeout after 300s",
+ "seconds": 300,
+ "cost": null,
+ "started_at": "2026-09-28T05:25:05.646Z",
+ "finished_at": "2026-09-28T05:30:05.998Z",
+ "queued_at": "2026-09-28T05:20:05.227Z",
+ "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3-Next-80B-A3B-Instruct-4bit)"
+ },
+ {
+ "model": "exo__qwen3-vl-4b-instruct-4bit",
+ "status": "error",
+ "error": "timeout after 300s",
+ "seconds": 301,
+ "cost": null,
+ "started_at": "2026-09-28T05:30:06.522Z",
+ "finished_at": "2026-09-28T05:35:07.367Z",
+ "queued_at": "2026-09-28T05:20:05.261Z",
+ "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3-Next-80B-A3B-Instruct-4bit)"
+ },
+ {
+ "model": "exo__minimax-m2-7",
+ "status": "error",
+ "error": "timeout after 300s",
+ "seconds": 301,
+ "cost": null,
+ "started_at": "2026-09-28T05:35:07.954Z",
+ "finished_at": "2026-09-28T05:40:09.147Z",
+ "queued_at": "2026-09-28T05:20:05.295Z",
+ "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3-Next-80B-A3B-Instruct-4bit)"
+ }
+ ],
+ "judging": false,
+ "aiPick": null,
+ "judged_at": "2026-09-28T05:40:09.452Z"
}
]
\ No newline at end of file
diff --git a/yolo/arena-loop-state.json b/yolo/arena-loop-state.json
index fd9a57c..7373069 100644
--- a/yolo/arena-loop-state.json
+++ b/yolo/arena-loop-state.json
@@ -1 +1 @@
-{"promptIdx":3,"modelOffset":9,"compCount":{"Art":83,"Culture":82,"News":82,"Political Cartoon":82,"Games":41,"Real Work":41,"Data Viz":41,"Science":41,"Music":41,"Sports":41,"History":41,"Nature & Space":41,"Comedy":41,"Demoscene":41,"Finance":41,"Design":41},"catIdx":0,"perCat":{"Art":2,"Culture":2,"News":2,"Political Cartoon":2,"Games":2,"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":15,"compCount":{"Art":84,"Culture":82,"News":82,"Political Cartoon":82,"Games":41,"Real Work":41,"Data Viz":41,"Science":41,"Music":41,"Sports":41,"History":41,"Nature & Space":41,"Comedy":41,"Demoscene":41,"Finance":41,"Design":41},"catIdx":1,"perCat":{"Art":3,"Culture":2,"News":2,"Political Cartoon":2,"Games":2,"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
diff --git a/yolo/daily-log.jsonl b/yolo/daily-log.jsonl
index b011724..ecae5dc 100644
--- a/yolo/daily-log.jsonl
+++ b/yolo/daily-log.jsonl
@@ -915,3 +915,5 @@
{"ts":"2026-09-28T04:32:29.745Z","id":"6d00e2148cdd","promptId":"mondrian","category":"Art","title":"Art Competition #83 — Playable Mondrian","models":6,"done":2,"errored":4,"settled":true,"aiPick":null,"loop":true}
{"ts":"2026-09-28T04:51:10.284Z","id":"559bc69196d0","promptId":"culture-map","category":"Culture","title":"Culture Competition #82 — Festivals of Nowhere","models":4,"done":4,"errored":0,"settled":true,"aiPick":null,"loop":true}
{"ts":"2026-09-28T04:59:55.448Z","id":"e7c6f87cedb0","promptId":"econ-brief","category":"News","title":"News Competition #82 — Teletext Econ Briefing","models":4,"done":4,"errored":0,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-28T05:15:05.015Z","id":"703c8ad78a77","promptId":"satire-strip","category":"Political Cartoon","title":"Political Cartoon Competition #82 — The Form to Request a Form","models":6,"done":2,"errored":4,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-28T05:40:16.127Z","id":"85093a3aecdd","promptId":"kinetic-type","category":"Art","title":"Art Competition #84 — Swarm Typography Poster","models":6,"done":1,"errored":5,"settled":true,"aiPick":null,"loop":true}
← be08c17 auto-data-snapshot: 2026-09-27T22:09:52 (3 data files) — dat
·
back to Model Arena
·
auto-data-snapshot: 2026-09-27T23:11:00 (3 data files) — dat ab4d943 →