← back to Model Arena
auto-data-snapshot: 2026-09-20T05:34:32 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl
9c870d181afe35f8cea1793d475105a47015346d · 2026-09-20 05:36:21 -0700 · auto-commit-fleet
Files touched
M data/challenges.jsonM yolo/arena-loop-state.jsonM yolo/daily-log.jsonl
Diff
commit 9c870d181afe35f8cea1793d475105a47015346d
Author: auto-commit-fleet <steve@designerwallcoverings.com>
Date: Sun Sep 20 05:36:21 2026 -0700
auto-data-snapshot: 2026-09-20T05:34:32 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl
---
data/challenges.json | 363 ++++++++++++++++++++++++++++++++++++++++++++-
yolo/arena-loop-state.json | 2 +-
yolo/daily-log.jsonl | 6 +
3 files changed, 366 insertions(+), 5 deletions(-)
diff --git a/data/challenges.json b/data/challenges.json
index 192cc03..9956cfd 100644
--- a/data/challenges.json
+++ b/data/challenges.json
@@ -63857,12 +63857,12 @@
"runs": [
{
"model": "mlx__qwen3-next-80b-a3b-instruct-4bit",
- "status": "running",
- "error": null,
- "seconds": null,
+ "status": "error",
+ "error": "timeout after 600s",
+ "seconds": 600,
"cost": null,
"started_at": "2026-09-20T11:59:42.660Z",
- "finished_at": null,
+ "finished_at": "2026-09-20T12:09:42.808Z",
"queued_at": "2026-09-20T11:59:42.262Z"
},
{
@@ -63916,5 +63916,360 @@
"queued_at": "2026-09-20T11:59:42.627Z"
}
]
+ },
+ {
+ "id": "7152ae7abfdc",
+ "title": "Data Viz Competition #19 — 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": "2026-09-20T12:14:43.140Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "exo__qwen3-6-35b-a3b-bf16",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T12:14:43.370Z",
+ "finished_at": "2026-09-20T12:14:43.403Z",
+ "queued_at": "2026-09-20T12:14:43.171Z"
+ },
+ {
+ "model": "exo__qwen3-vl-4b-instruct-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T12:14:43.432Z",
+ "finished_at": "2026-09-20T12:14:43.464Z",
+ "queued_at": "2026-09-20T12:14:43.203Z"
+ },
+ {
+ "model": "exo__minimax-m2-7",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T12:14:43.485Z",
+ "finished_at": "2026-09-20T12:14:43.513Z",
+ "queued_at": "2026-09-20T12:14:43.238Z"
+ },
+ {
+ "model": "exo__llama-3-3-70b-instruct-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T12:14:43.533Z",
+ "finished_at": "2026-09-20T12:14:43.555Z",
+ "queued_at": "2026-09-20T12:14:43.279Z"
+ },
+ {
+ "model": "exo__gemma-4-e2b-it-bf16",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T12:14:43.574Z",
+ "finished_at": "2026-09-20T12:14:43.597Z",
+ "queued_at": "2026-09-20T12:14:43.302Z"
+ },
+ {
+ "model": "exo__qwen3-next-80b-a3b-instruct-8bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T12:14:43.615Z",
+ "finished_at": "2026-09-20T12:14:43.663Z",
+ "queued_at": "2026-09-20T12:14:43.347Z"
+ }
+ ]
+ },
+ {
+ "id": "5c8cf8178a3d",
+ "title": "Science Competition #19 — 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": "2026-09-20T12:19:51.405Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "exo__qwen3-6-27b-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T12:19:51.574Z",
+ "finished_at": "2026-09-20T12:19:51.597Z",
+ "queued_at": "2026-09-20T12:19:51.441Z"
+ },
+ {
+ "model": "exo__glm-4-7-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T12:19:51.617Z",
+ "finished_at": "2026-09-20T12:19:51.639Z",
+ "queued_at": "2026-09-20T12:19:51.467Z"
+ },
+ {
+ "model": "exo__gemma-4-31b-it-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T12:19:51.662Z",
+ "finished_at": "2026-09-20T12:19:51.689Z",
+ "queued_at": "2026-09-20T12:19:51.489Z"
+ },
+ {
+ "model": "exo__nvidia-nemotron-3-nano-30b-a3b-mlx-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T12:19:51.716Z",
+ "finished_at": "2026-09-20T12:19:51.749Z",
+ "queued_at": "2026-09-20T12:19:51.509Z"
+ },
+ {
+ "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": "2026-09-20T12:19:51.778Z",
+ "finished_at": "2026-09-20T12:19:51.810Z",
+ "queued_at": "2026-09-20T12:19:51.534Z"
+ },
+ {
+ "model": "exo__qwen3-coder-next-6bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T12:19:51.831Z",
+ "finished_at": "2026-09-20T12:19:51.854Z",
+ "queued_at": "2026-09-20T12:19:51.555Z"
+ }
+ ]
+ },
+ {
+ "id": "86744b54dbc9",
+ "title": "Music Competition #19 — 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": "2026-09-20T12:24:59.635Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "exo__step-3-5-flash-6bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T12:24:59.844Z",
+ "finished_at": "2026-09-20T12:24:59.885Z",
+ "queued_at": "2026-09-20T12:24:59.662Z"
+ },
+ {
+ "model": "exo__qwen3-next-80b-a3b-thinking-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T12:24:59.908Z",
+ "finished_at": "2026-09-20T12:24:59.946Z",
+ "queued_at": "2026-09-20T12:24:59.689Z"
+ },
+ {
+ "model": "exo__deepseek-v3-1-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T12:24:59.971Z",
+ "finished_at": "2026-09-20T12:24:59.999Z",
+ "queued_at": "2026-09-20T12:24:59.714Z"
+ },
+ {
+ "model": "exo__llama-3-1-nemotron-70b-instruct-hf-8bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T12:25:00.020Z",
+ "finished_at": "2026-09-20T12:25:00.042Z",
+ "queued_at": "2026-09-20T12:24:59.734Z"
+ },
+ {
+ "model": "exo__gemma-4-e4b-it-6bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T12:25:00.062Z",
+ "finished_at": "2026-09-20T12:25:00.094Z",
+ "queued_at": "2026-09-20T12:24:59.766Z"
+ },
+ {
+ "model": "exo__nvidia-nemotron-3-nano-30b-a3b-mlx-5bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T12:25:00.113Z",
+ "finished_at": "2026-09-20T12:25:00.143Z",
+ "queued_at": "2026-09-20T12:24:59.791Z"
+ }
+ ]
+ },
+ {
+ "id": "0e60af4eba0c",
+ "title": "Sports Competition #19 — Zero-G Relay League",
+ "prompt": "Build this as one complete, self-contained HTML file: A standings tracker for an INVENTED sport (zero-gravity relay) with a sortable table, a form guide of tiny animated results, and a team page that shows their home 'arena' as a themed backdrop. 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": "Sports",
+ "designTools": false,
+ "created_at": "2026-09-20T12:30:07.877Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "exo__glm-4-7-flash-6bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T12:30:08.101Z",
+ "finished_at": "2026-09-20T12:30:08.141Z",
+ "queued_at": "2026-09-20T12:30:07.911Z"
+ },
+ {
+ "model": "exo__qwen3-5-35b-a3b-8bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T12:30:08.188Z",
+ "finished_at": "2026-09-20T12:30:08.240Z",
+ "queued_at": "2026-09-20T12:30:07.946Z"
+ },
+ {
+ "model": "exo__glm-4-7-8bit-gs32",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T12:30:08.277Z",
+ "finished_at": "2026-09-20T12:30:08.329Z",
+ "queued_at": "2026-09-20T12:30:07.977Z"
+ },
+ {
+ "model": "exo__glm-5-1",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T12:30:08.375Z",
+ "finished_at": "2026-09-20T12:30:08.425Z",
+ "queued_at": "2026-09-20T12:30:08.000Z"
+ },
+ {
+ "model": "exo__kimi-k2-5",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T12:30:08.454Z",
+ "finished_at": "2026-09-20T12:30:08.496Z",
+ "queued_at": "2026-09-20T12:30:08.034Z"
+ },
+ {
+ "model": "exo__qwen3-5-397b-a17b-8bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T12:30:08.542Z",
+ "finished_at": "2026-09-20T12:30:08.594Z",
+ "queued_at": "2026-09-20T12:30:08.072Z"
+ }
+ ]
+ },
+ {
+ "id": "6ccf4fbb7884",
+ "title": "History Competition #19 — Walk-Through Age of Invention",
+ "prompt": "Build this as one complete, self-contained HTML file: A scrollable timeline of an INVENTED age of invention where each era is a room you walk through, gadgets you can click to 'switch on', and a filter that dims everything except one thread of progress. 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": "History",
+ "designTools": false,
+ "created_at": "2026-09-20T12:35:16.134Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "exo__minimax-m2-7-5bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T12:35:16.289Z",
+ "finished_at": "2026-09-20T12:35:16.317Z",
+ "queued_at": "2026-09-20T12:35:16.156Z"
+ },
+ {
+ "model": "exo__qwen3-5-2b-mlx-8bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T12:35:16.342Z",
+ "finished_at": "2026-09-20T12:35:16.373Z",
+ "queued_at": "2026-09-20T12:35:16.175Z"
+ },
+ {
+ "model": "exo__deepseek-v3-2-8bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T12:35:16.406Z",
+ "finished_at": "2026-09-20T12:35:16.432Z",
+ "queued_at": "2026-09-20T12:35:16.194Z"
+ },
+ {
+ "model": "exo__qwen3-5-27b-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T12:35:16.464Z",
+ "finished_at": "2026-09-20T12:35:16.496Z",
+ "queued_at": "2026-09-20T12:35:16.214Z"
+ },
+ {
+ "model": "exo__gemma-4-e2b-it-8bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T12:35:16.531Z",
+ "finished_at": "2026-09-20T12:35:16.570Z",
+ "queued_at": "2026-09-20T12:35:16.234Z"
+ },
+ {
+ "model": "exo__qwen3-coder-next-5bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T12:35:16.593Z",
+ "finished_at": "2026-09-20T12:35:16.621Z",
+ "queued_at": "2026-09-20T12:35:16.260Z"
+ }
+ ]
}
]
\ No newline at end of file
diff --git a/yolo/arena-loop-state.json b/yolo/arena-loop-state.json
index 7e0389a..b6ca8ee 100644
--- a/yolo/arena-loop-state.json
+++ b/yolo/arena-loop-state.json
@@ -1 +1 @@
-{"promptIdx":3,"modelOffset":10,"compCount":{"Art":38,"Culture":37,"News":37,"Political Cartoon":37,"Games":19,"Real Work":19,"Data Viz":18,"Science":18,"Music":18,"Sports":18,"History":18,"Nature & Space":18,"Comedy":18,"Demoscene":18,"Finance":18,"Design":18},"catIdx":6,"perCat":{"Art":1,"Culture":1,"News":1,"Political Cartoon":1,"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":40,"compCount":{"Art":38,"Culture":37,"News":37,"Political Cartoon":37,"Games":19,"Real Work":19,"Data Viz":19,"Science":19,"Music":19,"Sports":19,"History":19,"Nature & Space":18,"Comedy":18,"Demoscene":18,"Finance":18,"Design":18},"catIdx":11,"perCat":{"Art":1,"Culture":1,"News":1,"Political Cartoon":1,"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
diff --git a/yolo/daily-log.jsonl b/yolo/daily-log.jsonl
index 8c71aef..e4e4655 100644
--- a/yolo/daily-log.jsonl
+++ b/yolo/daily-log.jsonl
@@ -420,3 +420,9 @@
{"ts":"2026-09-20T11:34:31.871Z","id":"457807d5a2dd","promptId":"election-viz","category":"News","title":"News Competition #37 — Election Night: Floating Isles","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
{"ts":"2026-09-20T11:39:40.415Z","id":"b37d5ef04e64","promptId":"editorial-cartoon","category":"Political Cartoon","title":"Political Cartoon Competition #37 — The Seesaw Debate","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
{"ts":"2026-09-20T11:54:41.698Z","id":"08a1b73bf7ac","promptId":"snake","category":"Games","title":"Games Competition #19 — Comet Snake in a Dying Galaxy","models":6,"done":1,"errored":5,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-20T12:09:43.087Z","id":"751e060ad25a","promptId":"crm","category":"Real Work","title":"Real Work Competition #19 — Fishing-Dock CRM","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-20T12:14:51.374Z","id":"7152ae7abfdc","promptId":"multi-chart","category":"Data Viz","title":"Data Viz Competition #19 — City of Data Dashboard","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-20T12:19:59.578Z","id":"5c8cf8178a3d","promptId":"solar","category":"Science","title":"Science Competition #19 — Conduct the Solar System","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-20T12:25:07.848Z","id":"86744b54dbc9","promptId":"sequencer","category":"Music","title":"Music Competition #19 — Constellation Sequencer","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-20T12:30:16.105Z","id":"0e60af4eba0c","promptId":"standings","category":"Sports","title":"Sports Competition #19 — Zero-G Relay League","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-20T12:35:24.297Z","id":"6ccf4fbb7884","promptId":"timeline-hist","category":"History","title":"History Competition #19 — Walk-Through Age of Invention","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
← fd6c7c9 auto-data-snapshot: 2026-09-20T05:01:07 (3 data files) — dat
·
back to Model Arena
·
auto-data-snapshot: 2026-09-20T06:08:12 (3 data files) — dat 3220b2d →