← back to Model Arena
auto-data-snapshot: 2026-09-18T22:19:26 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl
df3385aed972e533fd9e44b6567a7aa8b9c91ca4 · 2026-09-18 22:20:35 -0700 · auto-commit-fleet
Files touched
M data/challenges.jsonM yolo/arena-loop-state.jsonM yolo/daily-log.jsonl
Diff
commit df3385aed972e533fd9e44b6567a7aa8b9c91ca4
Author: auto-commit-fleet <steve@designerwallcoverings.com>
Date: Fri Sep 18 22:20:35 2026 -0700
auto-data-snapshot: 2026-09-18T22:19:26 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl
---
data/challenges.json | 235 +++++++++++++++++++++++++++++++++++++++++++++
yolo/arena-loop-state.json | 2 +-
yolo/daily-log.jsonl | 3 +
3 files changed, 239 insertions(+), 1 deletion(-)
diff --git a/data/challenges.json b/data/challenges.json
index 12c5545..94e5229 100644
--- a/data/challenges.json
+++ b/data/challenges.json
@@ -42201,5 +42201,240 @@
"queued_at": "2026-09-19T04:45:05.380Z"
}
]
+ },
+ {
+ "id": "8d0aa0517f69",
+ "title": "Political Cartoon Competition #7 — Ship of State by Committee",
+ "prompt": "Build this as one complete, self-contained HTML file: A single bold SVG metaphor illustration for an INVENTED political theme — 'the ship of state steered by committee' — where dragging elements changes the metaphor's meaning and the caption adapts. Light/dark toggle. 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": "Political Cartoon",
+ "designTools": false,
+ "created_at": "2026-09-19T04:50:13.432Z",
+ "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": "2026-09-19T04:50:13.517Z",
+ "finished_at": "2026-09-19T04:50:13.543Z",
+ "queued_at": "2026-09-19T04:50:13.453Z"
+ },
+ {
+ "model": "exo__gemma-4-31b-it-8bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T04:50:13.549Z",
+ "finished_at": "2026-09-19T04:50:13.560Z",
+ "queued_at": "2026-09-19T04:50:13.469Z"
+ },
+ {
+ "model": "qwen3-14b",
+ "status": "done",
+ "error": null,
+ "seconds": 146,
+ "cost": 0,
+ "started_at": "2026-09-19T04:50:13.523Z",
+ "finished_at": "2026-09-19T04:52:39.626Z",
+ "queued_at": "2026-09-19T04:50:13.481Z",
+ "bytes": 9789,
+ "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": "2026-09-19T04:50:13.530Z",
+ "finished_at": "2026-09-19T05:00:13.540Z",
+ "queued_at": "2026-09-19T04:50:13.492Z"
+ },
+ {
+ "model": "exo__minimax-m2-7-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T04:50:13.566Z",
+ "finished_at": "2026-09-19T04:50:13.579Z",
+ "queued_at": "2026-09-19T04:50:13.502Z"
+ },
+ {
+ "model": "qwen25-7b",
+ "status": "done",
+ "error": null,
+ "seconds": 30,
+ "cost": 0,
+ "started_at": "2026-09-19T04:52:39.675Z",
+ "finished_at": "2026-09-19T04:53:10.050Z",
+ "queued_at": "2026-09-19T04:50:13.510Z",
+ "bytes": 3642,
+ "thumb": true,
+ "aiScore": null,
+ "aiReason": "judge failed: all vision panelists failed"
+ }
+ ],
+ "judging": false,
+ "aiPick": null,
+ "judged_at": "2026-09-19T05:00:13.656Z"
+ },
+ {
+ "id": "ade879e2ca44",
+ "title": "Games Competition #4 — Comet Snake in a Dying Galaxy",
+ "prompt": "Build this as one complete, self-contained HTML file: Snake, but the snake is a comet and the arena is a shrinking galaxy: eating stars grows your tail AND bends gravity, near-misses trigger slow-mo, and the high score is logged as a named 'constellation'. 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": "Games",
+ "designTools": false,
+ "created_at": "2026-09-19T05:05:13.804Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "mlx__qwen3-next-80b-a3b-instruct-4bit",
+ "status": "error",
+ "error": "timeout after 600s",
+ "seconds": 600,
+ "cost": null,
+ "started_at": "2026-09-19T05:05:13.869Z",
+ "finished_at": "2026-09-19T05:15:13.910Z",
+ "queued_at": "2026-09-19T05:05:13.828Z"
+ },
+ {
+ "model": "exo__qwen3-coder-480b-a35b-instruct-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T05:05:13.878Z",
+ "finished_at": "2026-09-19T05:05:13.906Z",
+ "queued_at": "2026-09-19T05:05:13.836Z"
+ },
+ {
+ "model": "mac1__minicpm-v-latest",
+ "status": "done",
+ "error": null,
+ "seconds": 15,
+ "cost": 0,
+ "started_at": "2026-09-19T05:05:13.885Z",
+ "finished_at": "2026-09-19T05:05:29.128Z",
+ "queued_at": "2026-09-19T05:05:13.842Z",
+ "bytes": 1962,
+ "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": "2026-09-19T05:05:13.913Z",
+ "finished_at": "2026-09-19T05:05:13.930Z",
+ "queued_at": "2026-09-19T05:05:13.848Z"
+ },
+ {
+ "model": "mac1__qwen2-5vl-7b",
+ "status": "done",
+ "error": null,
+ "seconds": 51,
+ "cost": 0,
+ "started_at": "2026-09-19T05:05:29.146Z",
+ "finished_at": "2026-09-19T05:06:20.011Z",
+ "queued_at": "2026-09-19T05:05:13.854Z",
+ "bytes": 6231,
+ "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": "2026-09-19T05:05:13.937Z",
+ "finished_at": "2026-09-19T05:05:13.947Z",
+ "queued_at": "2026-09-19T05:05:13.862Z"
+ }
+ ],
+ "judging": false,
+ "aiPick": null,
+ "judged_at": "2026-09-19T05:15:13.985Z"
+ },
+ {
+ "id": "8dea099ad458",
+ "title": "Real Work Competition #4 — Fishing-Dock CRM",
+ "prompt": "Build this as one complete, self-contained HTML file: A CRM where each lead is a fish on a line you drag between stages (Nibble -> Hooked -> Landed), per-stage totals shown as a catch tally, with search, quick-add, and validation. Playful but genuinely usable. 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": "2026-09-19T05:20:14.154Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "exo__qwen3-6-35b-a3b-bf16",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T05:20:14.213Z",
+ "finished_at": "2026-09-19T05:20:14.224Z",
+ "queued_at": "2026-09-19T05:20:14.168Z"
+ },
+ {
+ "model": "exo__qwen3-vl-4b-instruct-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T05:20:14.229Z",
+ "finished_at": "2026-09-19T05:20:14.239Z",
+ "queued_at": "2026-09-19T05:20:14.181Z"
+ },
+ {
+ "model": "exo__minimax-m2-7",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T05:20:14.244Z",
+ "finished_at": "2026-09-19T05:20:14.253Z",
+ "queued_at": "2026-09-19T05:20:14.189Z"
+ },
+ {
+ "model": "exo__llama-3-3-70b-instruct-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T05:20:14.259Z",
+ "finished_at": "2026-09-19T05:20:14.269Z",
+ "queued_at": "2026-09-19T05:20:14.196Z"
+ },
+ {
+ "model": "exo__gemma-4-e2b-it-bf16",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T05:20:14.274Z",
+ "finished_at": "2026-09-19T05:20:14.284Z",
+ "queued_at": "2026-09-19T05:20:14.202Z"
+ },
+ {
+ "model": "exo__qwen3-next-80b-a3b-instruct-8bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T05:20:14.289Z",
+ "finished_at": "2026-09-19T05:20:14.299Z",
+ "queued_at": "2026-09-19T05:20:14.207Z"
+ }
+ ]
}
]
\ No newline at end of file
diff --git a/yolo/arena-loop-state.json b/yolo/arena-loop-state.json
index 8491043..efbc4f3 100644
--- a/yolo/arena-loop-state.json
+++ b/yolo/arena-loop-state.json
@@ -1 +1 @@
-{"promptIdx":3,"modelOffset":127,"compCount":{"Art":8,"Culture":7,"News":7,"Political Cartoon":6,"Games":3,"Real Work":3,"Data Viz":3,"Science":3,"Music":3,"Sports":3,"History":3,"Nature & Space":3,"Comedy":3,"Demoscene":3,"Finance":3,"Design":3},"catIdx":3,"perCat":{"Art":3,"Culture":3,"News":3,"Political Cartoon":2,"Games":3,"Real Work":3,"Data Viz":3,"Science":3,"Music":3,"Sports":3,"History":3,"Nature & Space":3,"Comedy":3,"Demoscene":3,"Finance":3,"Design":3}}
\ No newline at end of file
+{"promptIdx":3,"modelOffset":16,"compCount":{"Art":8,"Culture":7,"News":7,"Political Cartoon":7,"Games":4,"Real Work":4,"Data Viz":3,"Science":3,"Music":3,"Sports":3,"History":3,"Nature & Space":3,"Comedy":3,"Demoscene":3,"Finance":3,"Design":3},"catIdx":6,"perCat":{"Art":3,"Culture":3,"News":3,"Political Cartoon":3,"Games":1,"Real Work":1,"Data Viz":3,"Science":3,"Music":3,"Sports":3,"History":3,"Nature & Space":3,"Comedy":3,"Demoscene":3,"Finance":3,"Design":3}}
\ No newline at end of file
diff --git a/yolo/daily-log.jsonl b/yolo/daily-log.jsonl
index 6f70a60..3c69e6c 100644
--- a/yolo/daily-log.jsonl
+++ b/yolo/daily-log.jsonl
@@ -117,3 +117,6 @@
{"ts":"2026-09-19T04:34:56.918Z","id":"7ccc07da9e34","promptId":"kinetic-type","category":"Art","title":"Art Competition #8 — Swarm Typography Poster","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
{"ts":"2026-09-19T04:40:04.996Z","id":"2d99adf582e0","promptId":"languages","category":"Culture","title":"Culture Competition #7 — The Last Speaker","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
{"ts":"2026-09-19T04:45:13.395Z","id":"58f372ffbb70","promptId":"news-ticker","category":"News","title":"News Competition #7 — Absurd 24-Hour News","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-19T05:00:13.765Z","id":"8d0aa0517f69","promptId":"metaphor","category":"Political Cartoon","title":"Political Cartoon Competition #7 — Ship of State by Committee","models":6,"done":2,"errored":4,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-19T05:15:14.127Z","id":"ade879e2ca44","promptId":"snake","category":"Games","title":"Games Competition #4 — Comet Snake in a Dying Galaxy","models":6,"done":2,"errored":4,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-19T05:20:22.215Z","id":"8dea099ad458","promptId":"crm","category":"Real Work","title":"Real Work Competition #4 — Fishing-Dock CRM","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
← bb7f9e7 auto-data-snapshot: 2026-09-18T21:47:54 (3 data files) — dat
·
back to Model Arena
·
auto-data-snapshot: 2026-09-18T22:51:13 (3 data files) — dat 663b95c →