← back to Model Arena
auto-data-snapshot: 2026-09-19T05:12:50 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl
e99ddc8aecdb6122e3c9b1d27acd72181d3c5704 · 2026-09-19 05:13:58 -0700 · auto-commit-fleet
Files touched
M data/challenges.jsonM yolo/arena-loop-state.jsonM yolo/daily-log.jsonl
Diff
commit e99ddc8aecdb6122e3c9b1d27acd72181d3c5704
Author: auto-commit-fleet <steve@designerwallcoverings.com>
Date: Sat Sep 19 05:13:58 2026 -0700
auto-data-snapshot: 2026-09-19T05:12:50 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl
---
data/challenges.json | 310 ++++++++++++++++++++++++++++++++++++++++++++-
yolo/arena-loop-state.json | 2 +-
yolo/daily-log.jsonl | 5 +
3 files changed, 310 insertions(+), 7 deletions(-)
diff --git a/data/challenges.json b/data/challenges.json
index 9336db3..e394cec 100644
--- a/data/challenges.json
+++ b/data/challenges.json
@@ -46932,16 +46932,18 @@
"finished_at": "2026-09-19T11:30:22.393Z",
"queued_at": "2026-09-19T11:29:38.457Z",
"bytes": 4603,
- "thumb": true
+ "thumb": true,
+ "aiScore": null,
+ "aiReason": "judge failed: all vision panelists failed"
},
{
"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": "2026-09-19T11:39:38.979Z",
- "finished_at": null,
+ "finished_at": "2026-09-19T11:49:39.026Z",
"queued_at": "2026-09-19T11:29:38.526Z"
},
{
@@ -46964,7 +46966,303 @@
"finished_at": "2026-09-19T11:30:34.748Z",
"queued_at": "2026-09-19T11:29:38.661Z",
"bytes": 931,
- "thumb": true
+ "thumb": true,
+ "aiScore": null,
+ "aiReason": "judge failed: all vision panelists failed"
+ }
+ ],
+ "judging": false,
+ "aiPick": null,
+ "judged_at": "2026-09-19T11:49:39.108Z"
+ },
+ {
+ "id": "f21052bdb5ac",
+ "title": "Sports Competition #7 — 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": "2026-09-19T11:54:39.583Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "exo__qwen3-5-122b-a10b-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T11:54:39.804Z",
+ "finished_at": "2026-09-19T11:54:39.844Z",
+ "queued_at": "2026-09-19T11:54:39.628Z"
+ },
+ {
+ "model": "mac1__qwen2-5vl-7b",
+ "status": "done",
+ "error": null,
+ "seconds": 56,
+ "cost": 0,
+ "started_at": "2026-09-19T11:54:39.826Z",
+ "finished_at": "2026-09-19T11:55:35.815Z",
+ "queued_at": "2026-09-19T11:54:39.676Z",
+ "bytes": 7031,
+ "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": "2026-09-19T11:54:39.858Z",
+ "finished_at": "2026-09-19T11:54:39.889Z",
+ "queued_at": "2026-09-19T11:54:39.710Z"
+ },
+ {
+ "model": "exo__qwen3-6-35b-a3b-bf16",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T11:54:39.903Z",
+ "finished_at": "2026-09-19T11:54:39.920Z",
+ "queued_at": "2026-09-19T11:54:39.742Z"
+ },
+ {
+ "model": "exo__qwen3-vl-4b-instruct-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T11:54:39.934Z",
+ "finished_at": "2026-09-19T11:54:39.960Z",
+ "queued_at": "2026-09-19T11:54:39.770Z"
+ },
+ {
+ "model": "exo__minimax-m2-7",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T11:54:39.980Z",
+ "finished_at": "2026-09-19T11:54:40.011Z",
+ "queued_at": "2026-09-19T11:54:39.786Z"
+ }
+ ],
+ "judging": false,
+ "aiPick": null,
+ "judged_at": "2026-09-19T11:55:38.276Z"
+ },
+ {
+ "id": "f73aed4b130b",
+ "title": "History Competition #7 — 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": "2026-09-19T12:00:35.869Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "exo__llama-3-3-70b-instruct-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T12:00:36.005Z",
+ "finished_at": "2026-09-19T12:00:36.063Z",
+ "queued_at": "2026-09-19T12:00:35.889Z"
+ },
+ {
+ "model": "exo__gemma-4-e2b-it-bf16",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T12:00:36.099Z",
+ "finished_at": "2026-09-19T12:00:36.125Z",
+ "queued_at": "2026-09-19T12:00:35.910Z"
+ },
+ {
+ "model": "exo__qwen3-next-80b-a3b-instruct-8bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T12:00:36.141Z",
+ "finished_at": "2026-09-19T12:00:36.165Z",
+ "queued_at": "2026-09-19T12:00:35.924Z"
+ },
+ {
+ "model": "exo__qwen3-6-27b-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T12:00:36.186Z",
+ "finished_at": "2026-09-19T12:00:36.209Z",
+ "queued_at": "2026-09-19T12:00:35.942Z"
+ },
+ {
+ "model": "exo__glm-4-7-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T12:00:36.229Z",
+ "finished_at": "2026-09-19T12:00:36.256Z",
+ "queued_at": "2026-09-19T12:00:35.969Z"
+ },
+ {
+ "model": "exo__gemma-4-31b-it-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T12:00:36.278Z",
+ "finished_at": "2026-09-19T12:00:36.302Z",
+ "queued_at": "2026-09-19T12:00:35.986Z"
+ }
+ ]
+ },
+ {
+ "id": "bab1bcd0eb58",
+ "title": "Nature & Space Competition #7 — 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": "2026-09-19T12:05:44.099Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "exo__nvidia-nemotron-3-nano-30b-a3b-mlx-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T12:05:44.237Z",
+ "finished_at": "2026-09-19T12:05:44.265Z",
+ "queued_at": "2026-09-19T12:05:44.120Z"
+ },
+ {
+ "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": "2026-09-19T12:05:44.281Z",
+ "finished_at": "2026-09-19T12:05:44.309Z",
+ "queued_at": "2026-09-19T12:05:44.144Z"
+ },
+ {
+ "model": "exo__qwen3-coder-next-6bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T12:05:44.326Z",
+ "finished_at": "2026-09-19T12:05:44.356Z",
+ "queued_at": "2026-09-19T12:05:44.166Z"
+ },
+ {
+ "model": "exo__step-3-5-flash-6bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T12:05:44.370Z",
+ "finished_at": "2026-09-19T12:05:44.401Z",
+ "queued_at": "2026-09-19T12:05:44.186Z"
+ },
+ {
+ "model": "exo__qwen3-next-80b-a3b-thinking-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T12:05:44.420Z",
+ "finished_at": "2026-09-19T12:05:44.447Z",
+ "queued_at": "2026-09-19T12:05:44.201Z"
+ },
+ {
+ "model": "exo__deepseek-v3-1-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T12:05:44.460Z",
+ "finished_at": "2026-09-19T12:05:44.486Z",
+ "queued_at": "2026-09-19T12:05:44.221Z"
+ }
+ ]
+ },
+ {
+ "id": "697d2df97c58",
+ "title": "Comedy Competition #7 — 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": "2026-09-19T12:10:52.291Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "exo__llama-3-1-nemotron-70b-instruct-hf-8bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T12:10:52.520Z",
+ "finished_at": "2026-09-19T12:10:52.592Z",
+ "queued_at": "2026-09-19T12:10:52.321Z"
+ },
+ {
+ "model": "exo__gemma-4-e4b-it-6bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T12:10:52.633Z",
+ "finished_at": "2026-09-19T12:10:52.675Z",
+ "queued_at": "2026-09-19T12:10:52.351Z"
+ },
+ {
+ "model": "exo__nvidia-nemotron-3-nano-30b-a3b-mlx-5bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T12:10:52.732Z",
+ "finished_at": "2026-09-19T12:10:52.776Z",
+ "queued_at": "2026-09-19T12:10:52.383Z"
+ },
+ {
+ "model": "exo__glm-4-7-flash-6bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T12:10:52.811Z",
+ "finished_at": "2026-09-19T12:10:52.851Z",
+ "queued_at": "2026-09-19T12:10:52.408Z"
+ },
+ {
+ "model": "exo__qwen3-5-35b-a3b-8bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T12:10:52.884Z",
+ "finished_at": "2026-09-19T12:10:52.921Z",
+ "queued_at": "2026-09-19T12:10:52.462Z"
+ },
+ {
+ "model": "exo__glm-4-7-8bit-gs32",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T12:10:52.966Z",
+ "finished_at": "2026-09-19T12:10:53.005Z",
+ "queued_at": "2026-09-19T12:10:52.493Z"
}
]
}
diff --git a/yolo/arena-loop-state.json b/yolo/arena-loop-state.json
index 1442350..651dfcd 100644
--- a/yolo/arena-loop-state.json
+++ b/yolo/arena-loop-state.json
@@ -1 +1 @@
-{"promptIdx":3,"modelOffset":7,"compCount":{"Art":14,"Culture":13,"News":13,"Political Cartoon":13,"Games":7,"Real Work":7,"Data Viz":7,"Science":7,"Music":7,"Sports":6,"History":6,"Nature & Space":6,"Comedy":6,"Demoscene":6,"Finance":6,"Design":6},"catIdx":9,"perCat":{"Art":1,"Culture":1,"News":1,"Political Cartoon":1,"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
+{"promptIdx":3,"modelOffset":31,"compCount":{"Art":14,"Culture":13,"News":13,"Political Cartoon":13,"Games":7,"Real Work":7,"Data Viz":7,"Science":7,"Music":7,"Sports":7,"History":7,"Nature & Space":7,"Comedy":7,"Demoscene":6,"Finance":6,"Design":6},"catIdx":13,"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":1,"Comedy":1,"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 b03e797..c29b215 100644
--- a/yolo/daily-log.jsonl
+++ b/yolo/daily-log.jsonl
@@ -182,3 +182,8 @@
{"ts":"2026-09-19T11:12:21.528Z","id":"002e11f046ea","promptId":"crm","category":"Real Work","title":"Real Work Competition #7 — Fishing-Dock CRM","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
{"ts":"2026-09-19T11:17:29.776Z","id":"1e16cf3734db","promptId":"multi-chart","category":"Data Viz","title":"Data Viz Competition #7 — City of Data Dashboard","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
{"ts":"2026-09-19T11:24:38.164Z","id":"efb1652c2a4f","promptId":"solar","category":"Science","title":"Science Competition #7 — Conduct the Solar System","models":6,"done":1,"errored":5,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-19T11:49:39.560Z","id":"abcdb201ed45","promptId":"sequencer","category":"Music","title":"Music Competition #7 — Constellation Sequencer","models":6,"done":2,"errored":4,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-19T11:55:35.843Z","id":"f21052bdb5ac","promptId":"standings","category":"Sports","title":"Sports Competition #7 — Zero-G Relay League","models":6,"done":1,"errored":5,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-19T12:00:44.007Z","id":"f73aed4b130b","promptId":"timeline-hist","category":"History","title":"History Competition #7 — Walk-Through Age of Invention","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-19T12:05:52.245Z","id":"bab1bcd0eb58","promptId":"starmap","category":"Nature & Space","title":"Nature & Space Competition #7 — Invent Your Own Constellations","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-19T12:11:00.529Z","id":"697d2df97c58","promptId":"meme","category":"Comedy","title":"Comedy Competition #7 — The Meme Generator That Fights Back","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
← a0f5d39 auto-data-snapshot: 2026-09-19T04:40:20 (3 data files) — dat
·
back to Model Arena
·
auto-data-snapshot: 2026-09-19T05:44:32 (3 data files) — dat a41af32 →