← back to Model Arena
auto-data-snapshot: 2026-09-19T11:34:41 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl
14bb2d880e3d892d41daf8b5a64f2f091487bda7 · 2026-09-19 11:35:50 -0700 · auto-commit-fleet
Files touched
M data/challenges.jsonM yolo/arena-loop-state.jsonM yolo/daily-log.jsonl
Diff
commit 14bb2d880e3d892d41daf8b5a64f2f091487bda7
Author: auto-commit-fleet <steve@designerwallcoverings.com>
Date: Sat Sep 19 11:35:50 2026 -0700
auto-data-snapshot: 2026-09-19T11:34:41 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl
---
data/challenges.json | 220 +++++++++++++++++++++++++++++++++++++++++++++
yolo/arena-loop-state.json | 2 +-
yolo/daily-log.jsonl | 3 +
3 files changed, 224 insertions(+), 1 deletion(-)
diff --git a/data/challenges.json b/data/challenges.json
index 1bfd8d9..1e381f2 100644
--- a/data/challenges.json
+++ b/data/challenges.json
@@ -51435,5 +51435,225 @@
"queued_at": "2026-09-19T18:04:02.223Z"
}
]
+ },
+ {
+ "id": "8f8bd775561d",
+ "title": "Nature & Space Competition #10 — 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": "2026-09-19T18:09:10.279Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "exo__deepseek-v4-pro",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T18:09:10.399Z",
+ "finished_at": "2026-09-19T18:09:10.420Z",
+ "queued_at": "2026-09-19T18:09:10.298Z"
+ },
+ {
+ "model": "exo__deepseek-v3-1-8bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T18:09:10.436Z",
+ "finished_at": "2026-09-19T18:09:10.456Z",
+ "queued_at": "2026-09-19T18:09:10.315Z"
+ },
+ {
+ "model": "exo__glm-5-8bit-mxfp8",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T18:09:10.479Z",
+ "finished_at": "2026-09-19T18:09:10.508Z",
+ "queued_at": "2026-09-19T18:09:10.330Z"
+ },
+ {
+ "model": "exo__nvidia-nemotron-3-nano-30b-a3b-mlx-mxfp4",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T18:09:10.534Z",
+ "finished_at": "2026-09-19T18:09:10.560Z",
+ "queued_at": "2026-09-19T18:09:10.348Z"
+ },
+ {
+ "model": "exo__llama-3-1-nemotron-nano-4b-v1-1-8bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T18:09:10.583Z",
+ "finished_at": "2026-09-19T18:09:10.606Z",
+ "queued_at": "2026-09-19T18:09:10.366Z"
+ },
+ {
+ "model": "exo__kimi-k2-6",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T18:09:10.628Z",
+ "finished_at": "2026-09-19T18:09:10.654Z",
+ "queued_at": "2026-09-19T18:09:10.382Z"
+ }
+ ]
+ },
+ {
+ "id": "4c1635200597",
+ "title": "Comedy Competition #10 — The Meme Generator That Fights Back",
+ "prompt": "Build this as one complete, self-contained HTML file: A meme generator that judges you: a sarcastic INVENTED critic meter rates your caption, suggests a worse one, and lets you export the final over selectable CSS-drawn backdrops with font controls. 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": "Comedy",
+ "designTools": false,
+ "created_at": "2026-09-19T18:14:18.630Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "exo__nvidia-nemotron-3-nano-30b-a3b-mlx-8bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T18:14:19.053Z",
+ "finished_at": "2026-09-19T18:14:19.183Z",
+ "queued_at": "2026-09-19T18:14:18.687Z"
+ },
+ {
+ "model": "exo__gemma-4-31b-it-8bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T18:14:19.215Z",
+ "finished_at": "2026-09-19T18:14:19.328Z",
+ "queued_at": "2026-09-19T18:14:18.758Z"
+ },
+ {
+ "model": "qwen3-14b",
+ "status": "done",
+ "error": null,
+ "seconds": 174,
+ "cost": 0,
+ "started_at": "2026-09-19T18:14:19.079Z",
+ "finished_at": "2026-09-19T18:17:12.859Z",
+ "queued_at": "2026-09-19T18:14:18.835Z",
+ "bytes": 11849,
+ "thumb": true,
+ "aiScore": null,
+ "aiReason": "judge failed: all vision panelists failed"
+ },
+ {
+ "model": "mlx__qwen3-30b-a3b-instruct-2507-4bit",
+ "status": "error",
+ "error": "timeout after 600s",
+ "seconds": 600,
+ "cost": null,
+ "started_at": "2026-09-19T18:14:19.096Z",
+ "finished_at": "2026-09-19T18:24:19.129Z",
+ "queued_at": "2026-09-19T18:14:18.905Z"
+ },
+ {
+ "model": "exo__minimax-m2-7-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T18:14:19.366Z",
+ "finished_at": "2026-09-19T18:14:19.473Z",
+ "queued_at": "2026-09-19T18:14:19.011Z"
+ },
+ {
+ "model": "qwen25-7b",
+ "status": "error",
+ "error": "ollama bad response: 503",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T18:17:12.896Z",
+ "finished_at": "2026-09-19T18:17:13.075Z",
+ "queued_at": "2026-09-19T18:14:19.036Z"
+ }
+ ],
+ "judging": false,
+ "aiPick": null,
+ "judged_at": "2026-09-19T18:24:19.241Z"
+ },
+ {
+ "id": "1752d724993b",
+ "title": "Demoscene Competition #10 — 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": "2026-09-19T18:29:19.432Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "mlx__qwen3-next-80b-a3b-instruct-4bit",
+ "status": "running",
+ "error": null,
+ "seconds": null,
+ "cost": null,
+ "started_at": "2026-09-19T18:29:19.558Z",
+ "finished_at": null,
+ "queued_at": "2026-09-19T18:29:19.451Z"
+ },
+ {
+ "model": "exo__qwen3-coder-480b-a35b-instruct-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T18:29:19.575Z",
+ "finished_at": "2026-09-19T18:29:19.613Z",
+ "queued_at": "2026-09-19T18:29:19.468Z"
+ },
+ {
+ "model": "mac1__minicpm-v-latest",
+ "status": "error",
+ "error": "ollama bad response: 503",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T18:29:19.591Z",
+ "finished_at": "2026-09-19T18:29:19.776Z",
+ "queued_at": "2026-09-19T18:29:19.487Z"
+ },
+ {
+ "model": "exo__qwen3-5-122b-a10b-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T18:29:19.629Z",
+ "finished_at": "2026-09-19T18:29:19.669Z",
+ "queued_at": "2026-09-19T18:29:19.504Z"
+ },
+ {
+ "model": "mac1__qwen2-5vl-7b",
+ "status": "error",
+ "error": "ollama bad response: 503",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T18:29:19.807Z",
+ "finished_at": "2026-09-19T18:29:19.982Z",
+ "queued_at": "2026-09-19T18:29:19.524Z"
+ },
+ {
+ "model": "exo__gemma-4-26b-a4b-it-6bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T18:29:19.703Z",
+ "finished_at": "2026-09-19T18:29:19.744Z",
+ "queued_at": "2026-09-19T18:29:19.541Z"
+ }
+ ]
}
]
\ No newline at end of file
diff --git a/yolo/arena-loop-state.json b/yolo/arena-loop-state.json
index 7fd10a5..0b65821 100644
--- a/yolo/arena-loop-state.json
+++ b/yolo/arena-loop-state.json
@@ -1 +1 @@
-{"promptIdx":3,"modelOffset":121,"compCount":{"Art":20,"Culture":19,"News":19,"Political Cartoon":19,"Games":10,"Real Work":10,"Data Viz":10,"Science":10,"Music":10,"Sports":10,"History":10,"Nature & Space":9,"Comedy":9,"Demoscene":9,"Finance":9,"Design":9},"catIdx":11,"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":3,"Comedy":3,"Demoscene":3,"Finance":3,"Design":3}}
\ No newline at end of file
+{"promptIdx":3,"modelOffset":10,"compCount":{"Art":20,"Culture":19,"News":19,"Political Cartoon":19,"Games":10,"Real Work":10,"Data Viz":10,"Science":10,"Music":10,"Sports":10,"History":10,"Nature & Space":10,"Comedy":10,"Demoscene":10,"Finance":9,"Design":9},"catIdx":14,"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":3,"Design":3}}
\ No newline at end of file
diff --git a/yolo/daily-log.jsonl b/yolo/daily-log.jsonl
index 8f2679b..558fc43 100644
--- a/yolo/daily-log.jsonl
+++ b/yolo/daily-log.jsonl
@@ -245,3 +245,6 @@
{"ts":"2026-09-19T17:48:45.409Z","id":"c86c5f910c8f","promptId":"solar","category":"Science","title":"Science Competition #10 — Conduct the Solar System","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
{"ts":"2026-09-19T17:53:53.645Z","id":"db94d9563b08","promptId":"sequencer","category":"Music","title":"Music Competition #10 — Constellation Sequencer","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
{"ts":"2026-09-19T17:59:01.957Z","id":"4b2df456268d","promptId":"standings","category":"Sports","title":"Sports Competition #10 — Zero-G Relay League","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-19T18:04:10.255Z","id":"a3937ade5395","promptId":"timeline-hist","category":"History","title":"History Competition #10 — Walk-Through Age of Invention","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-19T18:09:18.404Z","id":"8f8bd775561d","promptId":"starmap","category":"Nature & Space","title":"Nature & Space Competition #10 — Invent Your Own Constellations","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-19T18:24:19.369Z","id":"4c1635200597","promptId":"meme","category":"Comedy","title":"Comedy Competition #10 — The Meme Generator That Fights Back","models":6,"done":1,"errored":5,"settled":true,"aiPick":null,"loop":true}
← 0ff1886 auto-data-snapshot: 2026-09-19T11:03:02 (3 data files) — dat
·
back to Model Arena
·
auto-data-snapshot: 2026-09-19T12:06:31 (3 data files) — dat 816ea2f →