← back to Model Arena
auto-data-snapshot: 2026-09-21T07:45:09 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl
42d8c1f64049c868589963d0c7e611ff29715aa1 · 2026-09-21 07:46:11 -0700 · auto-commit-fleet
Files touched
M data/challenges.jsonM yolo/arena-loop-state.jsonM yolo/daily-log.jsonl
Diff
commit 42d8c1f64049c868589963d0c7e611ff29715aa1
Author: auto-commit-fleet <steve@designerwallcoverings.com>
Date: Mon Sep 21 07:46:11 2026 -0700
auto-data-snapshot: 2026-09-21T07:45:09 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl
---
data/challenges.json | 266 ++++++++++++++++++++++++++++++++++++++++++++-
yolo/arena-loop-state.json | 2 +-
yolo/daily-log.jsonl | 5 +
3 files changed, 267 insertions(+), 6 deletions(-)
diff --git a/data/challenges.json b/data/challenges.json
index 089fb1d..f61ecdd 100644
--- a/data/challenges.json
+++ b/data/challenges.json
@@ -82247,16 +82247,18 @@
"finished_at": "2026-09-21T14:09:39.689Z",
"queued_at": "2026-09-21T14:07:08.777Z",
"bytes": 10041,
- "thumb": true
+ "thumb": true,
+ "aiScore": null,
+ "aiReason": "judge failed: all vision panelists failed"
},
{
"model": "mlx__qwen3-30b-a3b-instruct-2507-4bit",
- "status": "running",
- "error": null,
- "seconds": null,
+ "status": "error",
+ "error": "timeout after 600s",
+ "seconds": 600,
"cost": null,
"started_at": "2026-09-21T14:07:09.032Z",
- "finished_at": null,
+ "finished_at": "2026-09-21T14:17:09.110Z",
"queued_at": "2026-09-21T14:07:08.818Z"
},
{
@@ -82279,6 +82281,260 @@
"finished_at": "2026-09-21T14:09:40.015Z",
"queued_at": "2026-09-21T14:07:08.893Z"
}
+ ],
+ "judging": false,
+ "aiPick": null,
+ "judged_at": "2026-09-21T14:17:09.229Z"
+ },
+ {
+ "id": "f3c502352bf6",
+ "title": "Daily · Real Work: Quote Builder",
+ "prompt": "Build this as one complete, self-contained HTML file: A polished quote builder with editable line items, quantity/price math, discount, tax, validation, and print view. Build for a defined audience and primary journey, using realistic content and a strong information hierarchy. Every visible control must work and return clear feedback; include relevant empty, error, and completion states. Make the result cohesive from 390px to 1440px, keyboard accessible with visible focus, and respectful of reduced motion. Make it work beautifully at both 390px and 1440px widths. Success means a first-time user understands the product, completes the core task, and can verify the outcome without instructions.",
+ "category": "Real Work",
+ "designTools": false,
+ "created_at": "2026-09-21T14:15:05.024Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "qwen3-14b",
+ "status": "done",
+ "error": null,
+ "seconds": 212,
+ "cost": 0,
+ "started_at": "2026-09-21T14:15:05.153Z",
+ "finished_at": "2026-09-21T14:18:37.148Z",
+ "queued_at": "2026-09-21T14:15:05.065Z",
+ "bytes": 15356,
+ "thumb": true,
+ "aiScore": null,
+ "aiReason": "judge failed: all vision panelists failed"
+ },
+ {
+ "model": "qwen25-7b",
+ "status": "error",
+ "error": "ollama bad response: 503",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T14:18:37.184Z",
+ "finished_at": "2026-09-21T14:18:37.396Z",
+ "queued_at": "2026-09-21T14:15:05.107Z"
+ }
+ ],
+ "judging": false,
+ "aiPick": null,
+ "judged_at": "2026-09-21T14:18:39.022Z"
+ },
+ {
+ "id": "1ff0d22a8fb5",
+ "title": "Political Cartoon Competition #63 — 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": "2026-09-21T14:22:09.450Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "mlx__qwen3-next-80b-a3b-instruct-4bit",
+ "status": "error",
+ "error": "timeout after 600s",
+ "seconds": 600,
+ "cost": null,
+ "started_at": "2026-09-21T14:22:09.767Z",
+ "finished_at": "2026-09-21T14:32:09.919Z",
+ "queued_at": "2026-09-21T14:22:09.509Z"
+ },
+ {
+ "model": "exo__qwen3-coder-480b-a35b-instruct-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T14:22:09.815Z",
+ "finished_at": "2026-09-21T14:22:09.942Z",
+ "queued_at": "2026-09-21T14:22:09.557Z"
+ },
+ {
+ "model": "mac1__minicpm-v-latest",
+ "status": "error",
+ "error": "ollama bad response: 503",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T14:22:09.852Z",
+ "finished_at": "2026-09-21T14:22:10.187Z",
+ "queued_at": "2026-09-21T14:22:09.605Z"
+ },
+ {
+ "model": "exo__qwen3-5-122b-a10b-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T14:22:09.981Z",
+ "finished_at": "2026-09-21T14:22:10.052Z",
+ "queued_at": "2026-09-21T14:22:09.650Z"
+ },
+ {
+ "model": "mac1__qwen2-5vl-7b",
+ "status": "error",
+ "error": "ollama bad response: 503",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T14:22:10.218Z",
+ "finished_at": "2026-09-21T14:22:10.421Z",
+ "queued_at": "2026-09-21T14:22:09.688Z"
+ },
+ {
+ "model": "exo__gemma-4-26b-a4b-it-6bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T14:22:10.139Z",
+ "finished_at": "2026-09-21T14:22:10.246Z",
+ "queued_at": "2026-09-21T14:22:09.734Z"
+ }
+ ]
+ },
+ {
+ "id": "454b2f61c523",
+ "title": "Games Competition #32 — Wake the Dragon Breakout",
+ "prompt": "Build this as one complete, self-contained HTML file: Brick-breaker where the bricks are a sleeping dragon's scales — knock them loose and the dragon slowly wakes (eyes open, breathing quickens). The paddle is a shield; a caught power-up briefly lets you paint new bricks. 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": "2026-09-21T14:37:10.246Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "exo__qwen3-6-35b-a3b-bf16",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T14:37:10.756Z",
+ "finished_at": "2026-09-21T14:37:10.845Z",
+ "queued_at": "2026-09-21T14:37:10.329Z"
+ },
+ {
+ "model": "exo__qwen3-vl-4b-instruct-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T14:37:10.938Z",
+ "finished_at": "2026-09-21T14:37:11.039Z",
+ "queued_at": "2026-09-21T14:37:10.411Z"
+ },
+ {
+ "model": "exo__minimax-m2-7",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T14:37:11.104Z",
+ "finished_at": "2026-09-21T14:37:11.216Z",
+ "queued_at": "2026-09-21T14:37:10.480Z"
+ },
+ {
+ "model": "exo__llama-3-3-70b-instruct-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T14:37:11.281Z",
+ "finished_at": "2026-09-21T14:37:11.371Z",
+ "queued_at": "2026-09-21T14:37:10.546Z"
+ },
+ {
+ "model": "exo__gemma-4-e2b-it-bf16",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T14:37:11.484Z",
+ "finished_at": "2026-09-21T14:37:11.565Z",
+ "queued_at": "2026-09-21T14:37:10.624Z"
+ },
+ {
+ "model": "exo__qwen3-next-80b-a3b-instruct-8bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T14:37:11.626Z",
+ "finished_at": "2026-09-21T14:37:11.726Z",
+ "queued_at": "2026-09-21T14:37:10.681Z"
+ }
+ ]
+ },
+ {
+ "id": "4822e9ce0bf0",
+ "title": "Real Work Competition #32 — Timesheet Garden",
+ "prompt": "Build this as one complete, self-contained HTML file: A timesheet that grows your week as a garden — each logged hour sprouts a plant in the right plot, overtime wilts, and an 'invoice' view harvests it into a clean printable total with rate math and validation. 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": "2026-09-21T14:42:18.800Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "exo__qwen3-6-27b-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T14:42:19.070Z",
+ "finished_at": "2026-09-21T14:42:19.131Z",
+ "queued_at": "2026-09-21T14:42:18.840Z"
+ },
+ {
+ "model": "exo__glm-4-7-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T14:42:19.193Z",
+ "finished_at": "2026-09-21T14:42:19.242Z",
+ "queued_at": "2026-09-21T14:42:18.868Z"
+ },
+ {
+ "model": "exo__gemma-4-31b-it-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T14:42:19.273Z",
+ "finished_at": "2026-09-21T14:42:19.309Z",
+ "queued_at": "2026-09-21T14:42:18.911Z"
+ },
+ {
+ "model": "exo__nvidia-nemotron-3-nano-30b-a3b-mlx-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T14:42:19.339Z",
+ "finished_at": "2026-09-21T14:42:19.388Z",
+ "queued_at": "2026-09-21T14:42:18.937Z"
+ },
+ {
+ "model": "exo__llama-3-1-nemotron-nano-4b-v1-1-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T14:42:19.449Z",
+ "finished_at": "2026-09-21T14:42:19.516Z",
+ "queued_at": "2026-09-21T14:42:18.961Z"
+ },
+ {
+ "model": "exo__qwen3-coder-next-6bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T14:42:19.562Z",
+ "finished_at": "2026-09-21T14:42:19.609Z",
+ "queued_at": "2026-09-21T14:42:19.009Z"
+ }
]
}
]
\ No newline at end of file
diff --git a/yolo/arena-loop-state.json b/yolo/arena-loop-state.json
index 22e15de..a18a4bf 100644
--- a/yolo/arena-loop-state.json
+++ b/yolo/arena-loop-state.json
@@ -1 +1 @@
-{"promptIdx":3,"modelOffset":4,"compCount":{"Art":64,"Culture":63,"News":63,"Political Cartoon":62,"Games":31,"Real Work":31,"Data Viz":31,"Science":31,"Music":31,"Sports":31,"History":31,"Nature & Space":31,"Comedy":31,"Demoscene":31,"Finance":31,"Design":31},"catIdx":3,"perCat":{"Art":3,"Culture":3,"News":3,"Political Cartoon":2,"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":1}}
\ No newline at end of file
+{"promptIdx":3,"modelOffset":22,"compCount":{"Art":64,"Culture":63,"News":63,"Political Cartoon":63,"Games":32,"Real Work":32,"Data Viz":31,"Science":31,"Music":31,"Sports":31,"History":31,"Nature & Space":31,"Comedy":31,"Demoscene":31,"Finance":31,"Design":31},"catIdx":6,"perCat":{"Art":3,"Culture":3,"News":3,"Political Cartoon":3,"Games":2,"Real Work":2,"Data Viz":1,"Science":1,"Music":1,"Sports":1,"History":1,"Nature & Space":1,"Comedy":1,"Demoscene":1,"Finance":1,"Design":1}}
\ No newline at end of file
diff --git a/yolo/daily-log.jsonl b/yolo/daily-log.jsonl
index 7a33ed0..b93046e 100644
--- a/yolo/daily-log.jsonl
+++ b/yolo/daily-log.jsonl
@@ -678,3 +678,8 @@
{"ts":"2026-09-21T13:51:51.915Z","id":"3e4a948c493c","promptId":"satire-strip","category":"Political Cartoon","title":"Political Cartoon Competition #62 — The Form to Request a Form","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
{"ts":"2026-09-21T13:57:00.267Z","id":"381095040235","promptId":"kinetic-type","category":"Art","title":"Art Competition #64 — Swarm Typography Poster","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
{"ts":"2026-09-21T14:02:08.576Z","id":"54ba55674555","promptId":"languages","category":"Culture","title":"Culture Competition #63 — The Last Speaker","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-21T14:17:09.409Z","id":"2648ff628126","promptId":"news-ticker","category":"News","title":"News Competition #63 — Absurd 24-Hour News","models":6,"done":1,"errored":5,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-21T14:18:41.286Z","id":"f3c502352bf6","promptId":"invoice","title":"Daily · Real Work: Quote Builder","done":1,"aiPick":null,"partial":false}
+{"ts":"2026-09-21T14:32:10.186Z","id":"1ff0d22a8fb5","promptId":"metaphor","category":"Political Cartoon","title":"Political Cartoon Competition #63 — Ship of State by Committee","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-21T14:37:18.764Z","id":"454b2f61c523","promptId":"breakout","category":"Games","title":"Games Competition #32 — Wake the Dragon Breakout","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-21T14:42:27.085Z","id":"4822e9ce0bf0","promptId":"timesheet","category":"Real Work","title":"Real Work Competition #32 — Timesheet Garden","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
← 94b3003 auto-data-snapshot: 2026-09-21T07:12:32 (3 data files) — dat
·
back to Model Arena
·
auto-data-snapshot: 2026-09-21T08:17:25 (3 data files) — dat f2df420 →