← back to Model Arena
auto-data-snapshot: 2026-09-27T07:37:50 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl
8695a1fd0d8b3fe53e15e5f11c24bf20763decb7 · 2026-09-27 07:38:17 -0700 · auto-commit-fleet
Files touched
M data/challenges.jsonM yolo/arena-loop-state.jsonM yolo/daily-log.jsonl
Diff
commit 8695a1fd0d8b3fe53e15e5f11c24bf20763decb7
Author: auto-commit-fleet <steve@designerwallcoverings.com>
Date: Sun Sep 27 07:38:17 2026 -0700
auto-data-snapshot: 2026-09-27T07:37:50 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl
---
data/challenges.json | 164 +++++++++++++++++++++++++++++++++++++++++++++
yolo/arena-loop-state.json | 2 +-
yolo/daily-log.jsonl | 1 +
3 files changed, 166 insertions(+), 1 deletion(-)
diff --git a/data/challenges.json b/data/challenges.json
index aeb4869..5446f28 100644
--- a/data/challenges.json
+++ b/data/challenges.json
@@ -97454,5 +97454,169 @@
"queued_at": "2026-09-27T13:38:38.597Z"
}
]
+ },
+ {
+ "id": "083feec65fb6",
+ "title": "Demoscene Competition #40 — Lava-Lamp Boot Screen",
+ "prompt": "Build this as one complete, self-contained HTML file: A demoscene plasma pretending to be a lava-lamp OS boot screen — fake loading messages scroll over palette-cycling plasma, a 'sync to beat' toggle pulses it, and an fps counter sits in the corner. Reduced-motion fallback. 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": "Demoscene",
+ "designTools": false,
+ "created_at": "2026-09-27T14:08:44.305Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "exo__nvidia-nemotron-3-nano-30b-a3b-mlx-8bit",
+ "status": "error",
+ "error": "timeout after 300s",
+ "seconds": 301,
+ "cost": null,
+ "started_at": "2026-09-27T14:08:45.275Z",
+ "finished_at": "2026-09-27T14:13:46.254Z",
+ "queued_at": "2026-09-27T14:08:44.473Z",
+ "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)"
+ },
+ {
+ "model": "exo__gemma-4-31b-it-8bit",
+ "status": "error",
+ "error": "timeout after 300s",
+ "seconds": 300,
+ "cost": null,
+ "started_at": "2026-09-27T14:13:46.305Z",
+ "finished_at": "2026-09-27T14:18:46.499Z",
+ "queued_at": "2026-09-27T14:08:44.620Z",
+ "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)"
+ },
+ {
+ "model": "qwen3-14b",
+ "status": "done",
+ "error": null,
+ "seconds": 153,
+ "cost": 0,
+ "started_at": "2026-09-27T14:08:45.463Z",
+ "finished_at": "2026-09-27T14:11:19.132Z",
+ "queued_at": "2026-09-27T14:08:44.798Z",
+ "bytes": 8486,
+ "thumb": true,
+ "aiScore": null,
+ "aiReason": "judge failed: all vision panelists failed"
+ },
+ {
+ "model": "mlx__qwen3-8-27b-8bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 300,
+ "cost": null,
+ "started_at": "2026-09-27T14:08:45.730Z",
+ "finished_at": "2026-09-27T14:13:46.020Z",
+ "queued_at": "2026-09-27T14:08:44.927Z",
+ "fellBack": "http://127.0.0.1:52415 (mlx-community/MiniMax-M2.7-4bit)"
+ },
+ {
+ "model": "exo__minimax-m2-7-4bit",
+ "status": "error",
+ "error": "timeout after 300s",
+ "seconds": 300,
+ "cost": null,
+ "started_at": "2026-09-27T14:18:46.551Z",
+ "finished_at": "2026-09-27T14:23:46.731Z",
+ "queued_at": "2026-09-27T14:08:45.070Z",
+ "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)"
+ },
+ {
+ "model": "qwen25-7b",
+ "status": "done",
+ "error": null,
+ "seconds": 50,
+ "cost": 0,
+ "started_at": "2026-09-27T14:11:19.429Z",
+ "finished_at": "2026-09-27T14:12:09.649Z",
+ "queued_at": "2026-09-27T14:08:45.146Z",
+ "bytes": 4077,
+ "thumb": true,
+ "aiScore": null,
+ "aiReason": "judge failed: all vision panelists failed"
+ }
+ ],
+ "judging": false,
+ "aiPick": null,
+ "judged_at": "2026-09-27T14:23:46.954Z"
+ },
+ {
+ "id": "6aa278ada14d",
+ "title": "Finance Competition #40 — Galactic Exchange Portfolio",
+ "prompt": "Build this as one complete, self-contained HTML file: A portfolio tracker for an INVENTED galactic exchange (holdings in 'moon deeds' and 'comet futures'): allocation donut as a planet system, a gain/loss aura, a sortable table, and a what-if rebalance slider that re-orbits everything. 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": "Finance",
+ "designTools": false,
+ "created_at": "2026-09-27T14:28:50.888Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "mlx__qwen3-30b-a3b-instruct-2507-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 300,
+ "cost": null,
+ "started_at": "2026-09-27T14:28:51.338Z",
+ "finished_at": "2026-09-27T14:33:51.611Z",
+ "queued_at": "2026-09-27T14:28:50.958Z",
+ "fellBack": "http://127.0.0.1:52415 (mlx-community/MiniMax-M2.7-4bit)"
+ },
+ {
+ "model": "exo__qwen3-coder-480b-a35b-instruct-4bit",
+ "status": "error",
+ "error": "timeout after 300s",
+ "seconds": 300,
+ "cost": null,
+ "started_at": "2026-09-27T14:28:51.395Z",
+ "finished_at": "2026-09-27T14:33:51.692Z",
+ "queued_at": "2026-09-27T14:28:51.030Z",
+ "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)"
+ },
+ {
+ "model": "mac1__minicpm-v-latest",
+ "status": "done",
+ "error": null,
+ "seconds": 15,
+ "cost": 0,
+ "started_at": "2026-09-27T14:28:51.462Z",
+ "finished_at": "2026-09-27T14:29:06.764Z",
+ "queued_at": "2026-09-27T14:28:51.114Z",
+ "bytes": 1577,
+ "thumb": true
+ },
+ {
+ "model": "mlx__qwen3-next-80b-a3b-instruct-4bit",
+ "status": "running",
+ "error": null,
+ "seconds": null,
+ "cost": null,
+ "started_at": "2026-09-27T14:33:51.648Z",
+ "finished_at": null,
+ "queued_at": "2026-09-27T14:28:51.186Z"
+ },
+ {
+ "model": "exo__qwen3-5-122b-a10b-4bit",
+ "status": "running",
+ "error": null,
+ "seconds": null,
+ "cost": null,
+ "started_at": "2026-09-27T14:33:51.732Z",
+ "finished_at": null,
+ "queued_at": "2026-09-27T14:28:51.232Z",
+ "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)"
+ },
+ {
+ "model": "mac1__qwen2-5vl-7b",
+ "status": "done",
+ "error": null,
+ "seconds": 49,
+ "cost": 0,
+ "started_at": "2026-09-27T14:29:06.869Z",
+ "finished_at": "2026-09-27T14:29:56.058Z",
+ "queued_at": "2026-09-27T14:28:51.270Z",
+ "bytes": 4628,
+ "thumb": true
+ }
+ ]
}
]
\ No newline at end of file
diff --git a/yolo/arena-loop-state.json b/yolo/arena-loop-state.json
index 05746f8..f376792 100644
--- a/yolo/arena-loop-state.json
+++ b/yolo/arena-loop-state.json
@@ -1 +1 @@
-{"promptIdx":3,"modelOffset":129,"compCount":{"Art":80,"Culture":79,"News":79,"Political Cartoon":79,"Games":40,"Real Work":40,"Data Viz":40,"Science":40,"Music":40,"Sports":40,"History":40,"Nature & Space":40,"Comedy":40,"Demoscene":39,"Finance":39,"Design":39},"catIdx":13,"perCat":{"Art":3,"Culture":3,"News":3,"Political Cartoon":3,"Games":1,"Real Work":1,"Data Viz":1,"Science":1,"Music":1,"Sports":1,"History":1,"Nature & Space":1,"Comedy":1,"Demoscene":3,"Finance":3,"Design":3}}
\ No newline at end of file
+{"promptIdx":3,"modelOffset":10,"compCount":{"Art":80,"Culture":79,"News":79,"Political Cartoon":79,"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":39},"catIdx":15,"perCat":{"Art":3,"Culture":3,"News":3,"Political Cartoon":3,"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":3}}
\ No newline at end of file
diff --git a/yolo/daily-log.jsonl b/yolo/daily-log.jsonl
index a014f7c..376ed8c 100644
--- a/yolo/daily-log.jsonl
+++ b/yolo/daily-log.jsonl
@@ -891,3 +891,4 @@
{"ts":"2026-09-27T12:58:35.392Z","id":"3059bd8fe2e0","promptId":"timeline-hist","category":"History","title":"History Competition #40 — Walk-Through Age of Invention","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
{"ts":"2026-09-27T13:33:38.200Z","id":"455616d6262c","promptId":"starmap","category":"Nature & Space","title":"Nature & Space Competition #40 — Invent Your Own Constellations","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
{"ts":"2026-09-27T14:03:44.091Z","id":"3eb8fde07f2c","promptId":"meme","category":"Comedy","title":"Comedy Competition #40 — The Meme Generator That Fights Back","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-27T14:23:50.849Z","id":"083feec65fb6","promptId":"plasma","category":"Demoscene","title":"Demoscene Competition #40 — Lava-Lamp Boot Screen","models":6,"done":2,"errored":4,"settled":true,"aiPick":null,"loop":true}
← 556ac87 auto-data-snapshot: 2026-09-27T07:07:19 (3 data files) — dat
·
back to Model Arena
·
auto-data-snapshot: 2026-09-27T08:08:22 (3 data files) — dat 41fd04e →