← back to Model Arena
auto-data-snapshot: 2026-09-21T12:04:46 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl
f7f29559375bc835ec62de261b0d03df606aba37 · 2026-09-21 12:05:46 -0700 · auto-commit-fleet
Files touched
M data/challenges.jsonM yolo/arena-loop-state.jsonM yolo/daily-log.jsonl
Diff
commit f7f29559375bc835ec62de261b0d03df606aba37
Author: auto-commit-fleet <steve@designerwallcoverings.com>
Date: Mon Sep 21 12:05:46 2026 -0700
auto-data-snapshot: 2026-09-21T12:04:46 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl
---
data/challenges.json | 228 ++++++++++++++++++++++++++++++++++++++++++++-
yolo/arena-loop-state.json | 2 +-
yolo/daily-log.jsonl | 4 +
3 files changed, 228 insertions(+), 6 deletions(-)
diff --git a/data/challenges.json b/data/challenges.json
index 00a346c..6797b52 100644
--- a/data/challenges.json
+++ b/data/challenges.json
@@ -85352,16 +85352,18 @@
"finished_at": "2026-09-21T18:32:29.820Z",
"queued_at": "2026-09-21T18:30:10.077Z",
"bytes": 9113,
- "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": "2026-09-21T18:30:10.255Z",
- "finished_at": null,
+ "finished_at": "2026-09-21T18:40:10.309Z",
"queued_at": "2026-09-21T18:30:10.105Z"
},
{
@@ -85384,6 +85386,222 @@
"finished_at": "2026-09-21T18:32:30.110Z",
"queued_at": "2026-09-21T18:30:10.167Z"
}
+ ],
+ "judging": false,
+ "aiPick": null,
+ "judged_at": "2026-09-21T18:40:10.481Z"
+ },
+ {
+ "id": "40cf8a11464a",
+ "title": "Data Viz Competition #34 — City of Data Dashboard",
+ "prompt": "Build this as one complete, self-contained HTML file: An INVENTED 'city of data' dashboard where bar charts are skyscrapers, a donut is a roundabout, and a line chart is the dusk skyline — one shared filter re-zones the whole city, with a legend and an empty 'ghost town' state. 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": "Data Viz",
+ "designTools": false,
+ "created_at": "2026-09-21T18:45:10.583Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "mlx__qwen3-next-80b-a3b-instruct-4bit",
+ "status": "error",
+ "error": "timeout after 600s",
+ "seconds": 600,
+ "cost": null,
+ "started_at": "2026-09-21T18:45:10.956Z",
+ "finished_at": "2026-09-21T18:55:11.082Z",
+ "queued_at": "2026-09-21T18:45:10.627Z"
+ },
+ {
+ "model": "exo__qwen3-coder-480b-a35b-instruct-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T18:45:11.008Z",
+ "finished_at": "2026-09-21T18:45:11.084Z",
+ "queued_at": "2026-09-21T18:45:10.685Z"
+ },
+ {
+ "model": "mac1__minicpm-v-latest",
+ "status": "error",
+ "error": "ollama bad response: 503",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T18:45:11.051Z",
+ "finished_at": "2026-09-21T18:45:11.250Z",
+ "queued_at": "2026-09-21T18:45:10.727Z"
+ },
+ {
+ "model": "exo__qwen3-5-122b-a10b-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T18:45:11.122Z",
+ "finished_at": "2026-09-21T18:45:11.171Z",
+ "queued_at": "2026-09-21T18:45:10.808Z"
+ },
+ {
+ "model": "mac1__qwen2-5vl-7b",
+ "status": "error",
+ "error": "ollama bad response: 503",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T18:45:11.295Z",
+ "finished_at": "2026-09-21T18:45:11.497Z",
+ "queued_at": "2026-09-21T18:45:10.863Z"
+ },
+ {
+ "model": "exo__gemma-4-26b-a4b-it-6bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T18:45:11.208Z",
+ "finished_at": "2026-09-21T18:45:11.348Z",
+ "queued_at": "2026-09-21T18:45:10.913Z"
+ }
+ ]
+ },
+ {
+ "id": "1f46b87b3cf9",
+ "title": "Science Competition #34 — Conduct the Solar System",
+ "prompt": "Build this as one complete, self-contained HTML file: An INVENTED solar system you conduct like an orchestra — each planet's orbit is a looping note, speed sets the tempo, clicking a world solos its sound with a fact card, and a 'supernova' resets it. Reduced-motion aware. 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": "Science",
+ "designTools": false,
+ "created_at": "2026-09-21T19:00:11.467Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "exo__qwen3-6-35b-a3b-bf16",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T19:00:11.714Z",
+ "finished_at": "2026-09-21T19:00:11.745Z",
+ "queued_at": "2026-09-21T19:00:11.517Z"
+ },
+ {
+ "model": "exo__qwen3-vl-4b-instruct-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T19:00:11.771Z",
+ "finished_at": "2026-09-21T19:00:11.810Z",
+ "queued_at": "2026-09-21T19:00:11.559Z"
+ },
+ {
+ "model": "exo__minimax-m2-7",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T19:00:11.837Z",
+ "finished_at": "2026-09-21T19:00:11.868Z",
+ "queued_at": "2026-09-21T19:00:11.599Z"
+ },
+ {
+ "model": "exo__llama-3-3-70b-instruct-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T19:00:11.911Z",
+ "finished_at": "2026-09-21T19:00:11.973Z",
+ "queued_at": "2026-09-21T19:00:11.626Z"
+ },
+ {
+ "model": "exo__gemma-4-e2b-it-bf16",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T19:00:12.019Z",
+ "finished_at": "2026-09-21T19:00:12.061Z",
+ "queued_at": "2026-09-21T19:00:11.658Z"
+ },
+ {
+ "model": "exo__qwen3-next-80b-a3b-instruct-8bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T19:00:12.101Z",
+ "finished_at": "2026-09-21T19:00:12.147Z",
+ "queued_at": "2026-09-21T19:00:11.687Z"
+ }
+ ]
+ },
+ {
+ "id": "ec6080507be9",
+ "title": "Music Competition #34 — Constellation Sequencer",
+ "prompt": "Build this as one complete, self-contained HTML file: A Web Audio step sequencer where the grid is a night sky and each active step is a star that flickers on its beat (patterns = constellations); tempo, swing, per-track mute, a shooting-star fill, and a safe muted default. 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": "Music",
+ "designTools": false,
+ "created_at": "2026-09-21T19:05:19.748Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "exo__qwen3-6-27b-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T19:05:20.133Z",
+ "finished_at": "2026-09-21T19:05:20.185Z",
+ "queued_at": "2026-09-21T19:05:19.789Z"
+ },
+ {
+ "model": "exo__glm-4-7-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T19:05:20.257Z",
+ "finished_at": "2026-09-21T19:05:20.326Z",
+ "queued_at": "2026-09-21T19:05:19.857Z"
+ },
+ {
+ "model": "exo__gemma-4-31b-it-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T19:05:20.382Z",
+ "finished_at": "2026-09-21T19:05:20.459Z",
+ "queued_at": "2026-09-21T19:05:19.937Z"
+ },
+ {
+ "model": "exo__nvidia-nemotron-3-nano-30b-a3b-mlx-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T19:05:20.507Z",
+ "finished_at": "2026-09-21T19:05:20.574Z",
+ "queued_at": "2026-09-21T19:05:19.967Z"
+ },
+ {
+ "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": "2026-09-21T19:05:20.646Z",
+ "finished_at": "2026-09-21T19:05:20.731Z",
+ "queued_at": "2026-09-21T19:05:20.008Z"
+ },
+ {
+ "model": "exo__qwen3-coder-next-6bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T19:05:20.792Z",
+ "finished_at": "2026-09-21T19:05:20.863Z",
+ "queued_at": "2026-09-21T19:05:20.046Z"
+ }
]
}
]
\ No newline at end of file
diff --git a/yolo/arena-loop-state.json b/yolo/arena-loop-state.json
index 3615282..8f76f1c 100644
--- a/yolo/arena-loop-state.json
+++ b/yolo/arena-loop-state.json
@@ -1 +1 @@
-{"promptIdx":3,"modelOffset":4,"compCount":{"Art":68,"Culture":67,"News":67,"Political Cartoon":67,"Games":34,"Real Work":34,"Data Viz":33,"Science":33,"Music":33,"Sports":33,"History":33,"Nature & Space":33,"Comedy":33,"Demoscene":33,"Finance":33,"Design":33},"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
+{"promptIdx":3,"modelOffset":22,"compCount":{"Art":68,"Culture":67,"News":67,"Political Cartoon":67,"Games":34,"Real Work":34,"Data Viz":34,"Science":34,"Music":34,"Sports":33,"History":33,"Nature & Space":33,"Comedy":33,"Demoscene":33,"Finance":33,"Design":33},"catIdx":9,"perCat":{"Art":3,"Culture":3,"News":3,"Political Cartoon":3,"Games":1,"Real Work":1,"Data Viz":1,"Science":1,"Music":1,"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 854f232..c91f311 100644
--- a/yolo/daily-log.jsonl
+++ b/yolo/daily-log.jsonl
@@ -722,3 +722,7 @@
{"ts":"2026-09-21T18:14:53.176Z","id":"d210845e524b","promptId":"news-ticker","category":"News","title":"News Competition #67 — Absurd 24-Hour News","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
{"ts":"2026-09-21T18:20:01.522Z","id":"e783ea892bdb","promptId":"metaphor","category":"Political Cartoon","title":"Political Cartoon Competition #67 — Ship of State by Committee","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
{"ts":"2026-09-21T18:25:09.934Z","id":"da2f976a90a6","promptId":"snake","category":"Games","title":"Games Competition #34 — Comet Snake in a Dying Galaxy","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-21T18:40:10.537Z","id":"d7316b9bbdbf","promptId":"crm","category":"Real Work","title":"Real Work Competition #34 — Fishing-Dock CRM","models":6,"done":1,"errored":5,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-21T18:55:11.256Z","id":"40cf8a11464a","promptId":"multi-chart","category":"Data Viz","title":"Data Viz Competition #34 — City of Data Dashboard","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-21T19:00:19.720Z","id":"1f46b87b3cf9","promptId":"solar","category":"Science","title":"Science Competition #34 — Conduct the Solar System","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-21T19:05:28.138Z","id":"ec6080507be9","promptId":"sequencer","category":"Music","title":"Music Competition #34 — Constellation Sequencer","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
← 7542957 auto-data-snapshot: 2026-09-21T11:31:47 (3 data files) — dat
·
back to Model Arena
·
auto-data-snapshot: 2026-09-21T12:37:32 (3 data files) — dat 90cd801 →