← back to Model Arena
auto-data-snapshot: 2026-09-20T07:48:13 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl
59d55f78d01c2ef17ba9929b06f476badb5947b4 · 2026-09-20 07:49:44 -0700 · auto-commit-fleet
Files touched
M data/challenges.jsonM yolo/arena-loop-state.jsonM yolo/daily-log.jsonl
Diff
commit 59d55f78d01c2ef17ba9929b06f476badb5947b4
Author: auto-commit-fleet <steve@designerwallcoverings.com>
Date: Sun Sep 20 07:49:44 2026 -0700
auto-data-snapshot: 2026-09-20T07:48:13 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl
---
data/challenges.json | 390 +++++++++++++++++++++++++++++++++++++++++++--
yolo/arena-loop-state.json | 2 +-
yolo/daily-log.jsonl | 7 +
3 files changed, 384 insertions(+), 15 deletions(-)
diff --git a/data/challenges.json b/data/challenges.json
index b6300aa..2c0007e 100644
--- a/data/challenges.json
+++ b/data/challenges.json
@@ -65385,12 +65385,12 @@
},
{
"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": "2026-09-20T14:09:52.995Z",
- "finished_at": null,
+ "finished_at": "2026-09-20T14:19:53.017Z",
"queued_at": "2026-09-20T13:59:52.842Z"
},
{
@@ -65426,24 +65426,386 @@
"runs": [
{
"model": "qwen3-14b",
- "status": "running",
+ "status": "done",
"error": null,
- "seconds": null,
- "cost": null,
+ "seconds": 145,
+ "cost": 0,
"started_at": "2026-09-20T14:15:00.879Z",
- "finished_at": null,
- "queued_at": "2026-09-20T14:15:00.823Z"
+ "finished_at": "2026-09-20T14:17:25.557Z",
+ "queued_at": "2026-09-20T14:15:00.823Z",
+ "bytes": 10106,
+ "thumb": true,
+ "aiScore": null,
+ "aiReason": "judge failed: all vision panelists failed"
},
{
"model": "qwen25-7b",
- "status": "queued",
- "error": null,
- "seconds": null,
+ "status": "error",
+ "error": "ollama bad response: 503",
+ "seconds": 0,
"cost": null,
- "started_at": null,
- "finished_at": null,
+ "started_at": "2026-09-20T14:17:25.597Z",
+ "finished_at": "2026-09-20T14:17:25.887Z",
"queued_at": "2026-09-20T14:15:00.849Z"
}
+ ],
+ "judging": false,
+ "aiPick": null,
+ "judged_at": "2026-09-20T14:17:27.523Z"
+ },
+ {
+ "id": "74644a5f800b",
+ "title": "Science Competition #20 — The Painting Pendulum",
+ "prompt": "Build this as one complete, self-contained HTML file: A double-pendulum that paints: its chaotic tip leaves luminous trails, so tiny tweaks to gravity/length spin wildly different artworks — with a 'twin start' mode that races two near-identical pendulums into divergence. 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": "2026-09-20T14:24:53.570Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "exo__qwen3-5-122b-a10b-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T14:24:53.872Z",
+ "finished_at": "2026-09-20T14:24:53.959Z",
+ "queued_at": "2026-09-20T14:24:53.622Z"
+ },
+ {
+ "model": "mac1__qwen2-5vl-7b",
+ "status": "error",
+ "error": "ollama bad response: 503",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T14:24:53.934Z",
+ "finished_at": "2026-09-20T14:24:54.180Z",
+ "queued_at": "2026-09-20T14:24:53.669Z"
+ },
+ {
+ "model": "exo__gemma-4-26b-a4b-it-6bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T14:24:53.987Z",
+ "finished_at": "2026-09-20T14:24:54.012Z",
+ "queued_at": "2026-09-20T14:24:53.715Z"
+ },
+ {
+ "model": "exo__qwen3-6-35b-a3b-bf16",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T14:24:54.030Z",
+ "finished_at": "2026-09-20T14:24:54.055Z",
+ "queued_at": "2026-09-20T14:24:53.757Z"
+ },
+ {
+ "model": "exo__qwen3-vl-4b-instruct-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T14:24:54.073Z",
+ "finished_at": "2026-09-20T14:24:54.097Z",
+ "queued_at": "2026-09-20T14:24:53.812Z"
+ },
+ {
+ "model": "exo__minimax-m2-7",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T14:24:54.137Z",
+ "finished_at": "2026-09-20T14:24:54.220Z",
+ "queued_at": "2026-09-20T14:24:53.838Z"
+ }
+ ]
+ },
+ {
+ "id": "6e2e6902f131",
+ "title": "Music Competition #20 — The Singing Creature Synth",
+ "prompt": "Build this as one complete, self-contained HTML file: A playable Web Audio synth built as a creature that sings: its mouth opens with amplitude, eyes track pitch, filter sweeps ruffle its fur, and the on-screen keys are its teeth. Waveform/envelope controls; genuinely playable. 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": "2026-09-20T14:30:01.916Z",
+ "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": "2026-09-20T14:30:02.258Z",
+ "finished_at": "2026-09-20T14:30:02.285Z",
+ "queued_at": "2026-09-20T14:30:01.961Z"
+ },
+ {
+ "model": "exo__gemma-4-e2b-it-bf16",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T14:30:02.338Z",
+ "finished_at": "2026-09-20T14:30:02.377Z",
+ "queued_at": "2026-09-20T14:30:02.017Z"
+ },
+ {
+ "model": "exo__qwen3-next-80b-a3b-instruct-8bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T14:30:02.399Z",
+ "finished_at": "2026-09-20T14:30:02.445Z",
+ "queued_at": "2026-09-20T14:30:02.064Z"
+ },
+ {
+ "model": "exo__qwen3-6-27b-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T14:30:02.485Z",
+ "finished_at": "2026-09-20T14:30:02.515Z",
+ "queued_at": "2026-09-20T14:30:02.121Z"
+ },
+ {
+ "model": "exo__glm-4-7-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T14:30:02.560Z",
+ "finished_at": "2026-09-20T14:30:02.647Z",
+ "queued_at": "2026-09-20T14:30:02.170Z"
+ },
+ {
+ "model": "exo__gemma-4-31b-it-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T14:30:02.694Z",
+ "finished_at": "2026-09-20T14:30:02.771Z",
+ "queued_at": "2026-09-20T14:30:02.218Z"
+ }
+ ]
+ },
+ {
+ "id": "ad7c93c6fa35",
+ "title": "Sports Competition #20 — Mascot Clash Bracket",
+ "prompt": "Build this as one complete, self-contained HTML file: A single-elim bracket for INVENTED mascots where clicking a winner triggers a 2-second SVG 'clash' animation before advancing, with seeding, highlighted upsets, and a champion confetti reveal. 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": "2026-09-20T14:35:10.301Z",
+ "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": "2026-09-20T14:35:10.588Z",
+ "finished_at": "2026-09-20T14:35:10.647Z",
+ "queued_at": "2026-09-20T14:35:10.341Z"
+ },
+ {
+ "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": "2026-09-20T14:35:10.688Z",
+ "finished_at": "2026-09-20T14:35:10.716Z",
+ "queued_at": "2026-09-20T14:35:10.385Z"
+ },
+ {
+ "model": "exo__qwen3-coder-next-6bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T14:35:10.767Z",
+ "finished_at": "2026-09-20T14:35:10.815Z",
+ "queued_at": "2026-09-20T14:35:10.424Z"
+ },
+ {
+ "model": "exo__step-3-5-flash-6bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T14:35:10.841Z",
+ "finished_at": "2026-09-20T14:35:10.892Z",
+ "queued_at": "2026-09-20T14:35:10.454Z"
+ },
+ {
+ "model": "exo__qwen3-next-80b-a3b-thinking-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T14:35:10.939Z",
+ "finished_at": "2026-09-20T14:35:10.973Z",
+ "queued_at": "2026-09-20T14:35:10.485Z"
+ },
+ {
+ "model": "exo__deepseek-v3-1-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T14:35:11.009Z",
+ "finished_at": "2026-09-20T14:35:11.035Z",
+ "queued_at": "2026-09-20T14:35:10.526Z"
+ }
+ ]
+ },
+ {
+ "id": "66cd4b4def99",
+ "title": "History Competition #20 — An Empire That Breathes",
+ "prompt": "Build this as one complete, self-contained HTML file: An INVENTED empire that breathes across a map as you drag a century slider — borders bloom and recede, cities rise as glowing dots, and event notes fade in at the turning points, with a legend. 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": "2026-09-20T14:40:18.625Z",
+ "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": "2026-09-20T14:40:18.904Z",
+ "finished_at": "2026-09-20T14:40:18.959Z",
+ "queued_at": "2026-09-20T14:40:18.660Z"
+ },
+ {
+ "model": "exo__gemma-4-e4b-it-6bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T14:40:18.983Z",
+ "finished_at": "2026-09-20T14:40:19.011Z",
+ "queued_at": "2026-09-20T14:40:18.714Z"
+ },
+ {
+ "model": "exo__nvidia-nemotron-3-nano-30b-a3b-mlx-5bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T14:40:19.033Z",
+ "finished_at": "2026-09-20T14:40:19.075Z",
+ "queued_at": "2026-09-20T14:40:18.756Z"
+ },
+ {
+ "model": "exo__glm-4-7-flash-6bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T14:40:19.107Z",
+ "finished_at": "2026-09-20T14:40:19.138Z",
+ "queued_at": "2026-09-20T14:40:18.814Z"
+ },
+ {
+ "model": "exo__qwen3-5-35b-a3b-8bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T14:40:19.178Z",
+ "finished_at": "2026-09-20T14:40:19.221Z",
+ "queued_at": "2026-09-20T14:40:18.857Z"
+ },
+ {
+ "model": "exo__glm-4-7-8bit-gs32",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T14:40:19.253Z",
+ "finished_at": "2026-09-20T14:40:19.314Z",
+ "queued_at": "2026-09-20T14:40:18.875Z"
+ }
+ ]
+ },
+ {
+ "id": "ce62a9bded1c",
+ "title": "Nature & Space Competition #20 — Terrarium in a Jar",
+ "prompt": "Build this as one complete, self-contained HTML file: A jar-terrarium ecosystem of INVENTED critters with live population graphs — feed them, introduce a predator, or trigger a drought and watch the food web wobble toward chaos or balance, with a reset. 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": "2026-09-20T14:45:26.945Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "exo__glm-5-1",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T14:45:27.156Z",
+ "finished_at": "2026-09-20T14:45:27.185Z",
+ "queued_at": "2026-09-20T14:45:26.982Z"
+ },
+ {
+ "model": "exo__kimi-k2-5",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T14:45:27.206Z",
+ "finished_at": "2026-09-20T14:45:27.228Z",
+ "queued_at": "2026-09-20T14:45:27.015Z"
+ },
+ {
+ "model": "exo__qwen3-5-397b-a17b-8bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T14:45:27.248Z",
+ "finished_at": "2026-09-20T14:45:27.269Z",
+ "queued_at": "2026-09-20T14:45:27.042Z"
+ },
+ {
+ "model": "exo__minimax-m2-7-5bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T14:45:27.293Z",
+ "finished_at": "2026-09-20T14:45:27.315Z",
+ "queued_at": "2026-09-20T14:45:27.074Z"
+ },
+ {
+ "model": "exo__qwen3-5-2b-mlx-8bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T14:45:27.336Z",
+ "finished_at": "2026-09-20T14:45:27.359Z",
+ "queued_at": "2026-09-20T14:45:27.103Z"
+ },
+ {
+ "model": "exo__deepseek-v3-2-8bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T14:45:27.377Z",
+ "finished_at": "2026-09-20T14:45:27.400Z",
+ "queued_at": "2026-09-20T14:45:27.129Z"
+ }
]
}
]
\ No newline at end of file
diff --git a/yolo/arena-loop-state.json b/yolo/arena-loop-state.json
index 86e7e0f..59cde92 100644
--- a/yolo/arena-loop-state.json
+++ b/yolo/arena-loop-state.json
@@ -1 +1 @@
-{"promptIdx":3,"modelOffset":7,"compCount":{"Art":40,"Culture":39,"News":39,"Political Cartoon":39,"Games":20,"Real Work":20,"Data Viz":20,"Science":19,"Music":19,"Sports":19,"History":19,"Nature & Space":19,"Comedy":19,"Demoscene":19,"Finance":19,"Design":19},"catIdx":7,"perCat":{"Art":3,"Culture":3,"News":3,"Political Cartoon":3,"Games":2,"Real Work":2,"Data Viz":2,"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":37,"compCount":{"Art":40,"Culture":39,"News":39,"Political Cartoon":39,"Games":20,"Real Work":20,"Data Viz":20,"Science":20,"Music":20,"Sports":20,"History":20,"Nature & Space":20,"Comedy":19,"Demoscene":19,"Finance":19,"Design":19},"catIdx":12,"perCat":{"Art":3,"Culture":3,"News":3,"Political Cartoon":3,"Games":2,"Real Work":2,"Data Viz":2,"Science":2,"Music":2,"Sports":2,"History":2,"Nature & Space":2,"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 24ae521..ed183a9 100644
--- a/yolo/daily-log.jsonl
+++ b/yolo/daily-log.jsonl
@@ -441,3 +441,10 @@
{"ts":"2026-09-20T13:42:11.953Z","id":"c409f538fd93","promptId":"metaphor","category":"Political Cartoon","title":"Political Cartoon Competition #39 — Ship of State by Committee","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
{"ts":"2026-09-20T13:47:20.272Z","id":"0b77e4a79e5c","promptId":"breakout","category":"Games","title":"Games Competition #20 — Wake the Dragon Breakout","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
{"ts":"2026-09-20T13:54:52.661Z","id":"dbf544d44149","promptId":"timesheet","category":"Real Work","title":"Real Work Competition #20 — Timesheet Garden","models":6,"done":1,"errored":5,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-20T14:17:32.952Z","id":"5b861ca6803f","promptId":"moodboard","title":"Daily · Creative Tools: Moodboard Composer","done":1,"aiPick":null,"partial":false}
+{"ts":"2026-09-20T14:19:53.527Z","id":"66bbf490ea69","promptId":"flow-infographic","category":"Data Viz","title":"Data Viz Competition #20 — Bean-to-Cup Sankey","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-20T14:25:01.878Z","id":"74644a5f800b","promptId":"pendulum","category":"Science","title":"Science Competition #20 — The Painting Pendulum","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-20T14:30:10.262Z","id":"6e2e6902f131","promptId":"synth","category":"Music","title":"Music Competition #20 — The Singing Creature Synth","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-20T14:35:18.591Z","id":"ad7c93c6fa35","promptId":"bracket","category":"Sports","title":"Sports Competition #20 — Mascot Clash Bracket","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-20T14:40:26.909Z","id":"66cd4b4def99","promptId":"empire-map","category":"History","title":"History Competition #20 — An Empire That Breathes","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-20T14:45:35.161Z","id":"ce62a9bded1c","promptId":"ecosystem","category":"Nature & Space","title":"Nature & Space Competition #20 — Terrarium in a Jar","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
← 15777c5 auto-data-snapshot: 2026-09-20T07:15:24 (3 data files) — dat
·
back to Model Arena
·
auto-data-snapshot: 2026-09-20T08:21:12 (3 data files) — dat fbab7de →