← back to Model Arena
auto-data-snapshot: 2026-09-20T10:00:50 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl
020054e24067572c09ab65728fe5753dfcb98277 · 2026-09-20 10:02:36 -0700 · auto-commit-fleet
Files touched
M data/challenges.jsonM yolo/arena-loop-state.jsonM yolo/daily-log.jsonl
Diff
commit 020054e24067572c09ab65728fe5753dfcb98277
Author: auto-commit-fleet <steve@designerwallcoverings.com>
Date: Sun Sep 20 10:02:36 2026 -0700
auto-data-snapshot: 2026-09-20T10:00:50 (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 c9c1b4c..8214cba 100644
--- a/data/challenges.json
+++ b/data/challenges.json
@@ -66962,12 +66962,12 @@
"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": "2026-09-20T16:22:40.905Z",
- "finished_at": null,
+ "finished_at": "2026-09-20T16:32:41.127Z",
"queued_at": "2026-09-20T16:22:40.617Z"
},
{
@@ -67021,5 +67021,360 @@
"queued_at": "2026-09-20T16:22:40.853Z"
}
]
+ },
+ {
+ "id": "f9e65b23682d",
+ "title": "Sports Competition #21 — Holographic Stat Cards",
+ "prompt": "Build this as one complete, self-contained HTML file: A trading-card stat viewer for INVENTED athletes: cards tilt in 3D to the cursor with a holographic sheen, flip to reveal radar stats, and a head-to-head mode slams two cards together for a winner readout. 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": "2026-09-20T16:37:41.357Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "exo__qwen3-6-35b-a3b-bf16",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T16:37:41.761Z",
+ "finished_at": "2026-09-20T16:37:41.798Z",
+ "queued_at": "2026-09-20T16:37:41.402Z"
+ },
+ {
+ "model": "exo__qwen3-vl-4b-instruct-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T16:37:41.826Z",
+ "finished_at": "2026-09-20T16:37:41.924Z",
+ "queued_at": "2026-09-20T16:37:41.451Z"
+ },
+ {
+ "model": "exo__minimax-m2-7",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T16:37:42.010Z",
+ "finished_at": "2026-09-20T16:37:42.071Z",
+ "queued_at": "2026-09-20T16:37:41.502Z"
+ },
+ {
+ "model": "exo__llama-3-3-70b-instruct-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T16:37:42.122Z",
+ "finished_at": "2026-09-20T16:37:42.180Z",
+ "queued_at": "2026-09-20T16:37:41.584Z"
+ },
+ {
+ "model": "exo__gemma-4-e2b-it-bf16",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T16:37:42.230Z",
+ "finished_at": "2026-09-20T16:37:42.306Z",
+ "queued_at": "2026-09-20T16:37:41.644Z"
+ },
+ {
+ "model": "exo__qwen3-next-80b-a3b-instruct-8bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T16:37:42.353Z",
+ "finished_at": "2026-09-20T16:37:42.400Z",
+ "queued_at": "2026-09-20T16:37:41.728Z"
+ }
+ ]
+ },
+ {
+ "id": "fb8c803c92a6",
+ "title": "History Competition #21 — Spotlit Relic Viewer",
+ "prompt": "Build this as one complete, self-contained HTML file: A museum artifact viewer where an INVENTED relic rotates as a chunky CSS-3D object under a movable spotlight; click facets to reveal provenance and era context, with next/prev and a 'restore vs weathered' 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": "History",
+ "designTools": false,
+ "created_at": "2026-09-20T16:42:49.804Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "exo__qwen3-6-27b-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T16:42:50.056Z",
+ "finished_at": "2026-09-20T16:42:50.109Z",
+ "queued_at": "2026-09-20T16:42:49.831Z"
+ },
+ {
+ "model": "exo__glm-4-7-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T16:42:50.164Z",
+ "finished_at": "2026-09-20T16:42:50.205Z",
+ "queued_at": "2026-09-20T16:42:49.866Z"
+ },
+ {
+ "model": "exo__gemma-4-31b-it-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T16:42:50.234Z",
+ "finished_at": "2026-09-20T16:42:50.300Z",
+ "queued_at": "2026-09-20T16:42:49.914Z"
+ },
+ {
+ "model": "exo__nvidia-nemotron-3-nano-30b-a3b-mlx-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T16:42:50.360Z",
+ "finished_at": "2026-09-20T16:42:50.429Z",
+ "queued_at": "2026-09-20T16:42:49.954Z"
+ },
+ {
+ "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": "2026-09-20T16:42:50.480Z",
+ "finished_at": "2026-09-20T16:42:50.607Z",
+ "queued_at": "2026-09-20T16:42:49.987Z"
+ },
+ {
+ "model": "exo__qwen3-coder-next-6bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T16:42:50.656Z",
+ "finished_at": "2026-09-20T16:42:50.694Z",
+ "queued_at": "2026-09-20T16:42:50.018Z"
+ }
+ ]
+ },
+ {
+ "id": "bae9e031aca8",
+ "title": "Nature & Space Competition #21 — Shake-the-Snow-Globe Weather",
+ "prompt": "Build this as one complete, self-contained HTML file: A snow-globe weather visualizer you shake (click-drag) to trigger storms over an INVENTED tiny town; a dial cycles sun/rain/storm/snow with smooth transitions and the town reacts (umbrellas, lights). 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": "Nature & Space",
+ "designTools": false,
+ "created_at": "2026-09-20T16:47:58.103Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "exo__step-3-5-flash-6bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T16:47:58.445Z",
+ "finished_at": "2026-09-20T16:47:58.491Z",
+ "queued_at": "2026-09-20T16:47:58.141Z"
+ },
+ {
+ "model": "exo__qwen3-next-80b-a3b-thinking-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T16:47:58.570Z",
+ "finished_at": "2026-09-20T16:47:58.623Z",
+ "queued_at": "2026-09-20T16:47:58.209Z"
+ },
+ {
+ "model": "exo__deepseek-v3-1-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T16:47:58.685Z",
+ "finished_at": "2026-09-20T16:47:58.723Z",
+ "queued_at": "2026-09-20T16:47:58.254Z"
+ },
+ {
+ "model": "exo__llama-3-1-nemotron-70b-instruct-hf-8bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T16:47:58.778Z",
+ "finished_at": "2026-09-20T16:47:58.820Z",
+ "queued_at": "2026-09-20T16:47:58.325Z"
+ },
+ {
+ "model": "exo__gemma-4-e4b-it-6bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T16:47:58.868Z",
+ "finished_at": "2026-09-20T16:47:58.938Z",
+ "queued_at": "2026-09-20T16:47:58.359Z"
+ },
+ {
+ "model": "exo__nvidia-nemotron-3-nano-30b-a3b-mlx-5bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T16:47:59.004Z",
+ "finished_at": "2026-09-20T16:47:59.069Z",
+ "queued_at": "2026-09-20T16:47:58.401Z"
+ }
+ ]
+ },
+ {
+ "id": "34edc5cb1b5f",
+ "title": "Comedy Competition #21 — Roast or Toast Campfire",
+ "prompt": "Build this as one complete, self-contained HTML file: A good-natured 'Roast or Toast' campfire where a toggle sends compliments or playful roasts at escalating heat levels shown as literal flames, with shareable text and a 'mercy' button. Keep it kind. 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": "2026-09-20T16:53:06.495Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "exo__glm-4-7-flash-6bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T16:53:06.771Z",
+ "finished_at": "2026-09-20T16:53:06.801Z",
+ "queued_at": "2026-09-20T16:53:06.554Z"
+ },
+ {
+ "model": "exo__qwen3-5-35b-a3b-8bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T16:53:06.822Z",
+ "finished_at": "2026-09-20T16:53:06.853Z",
+ "queued_at": "2026-09-20T16:53:06.612Z"
+ },
+ {
+ "model": "exo__glm-4-7-8bit-gs32",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T16:53:06.883Z",
+ "finished_at": "2026-09-20T16:53:06.914Z",
+ "queued_at": "2026-09-20T16:53:06.665Z"
+ },
+ {
+ "model": "exo__glm-5-1",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T16:53:06.945Z",
+ "finished_at": "2026-09-20T16:53:06.982Z",
+ "queued_at": "2026-09-20T16:53:06.694Z"
+ },
+ {
+ "model": "exo__kimi-k2-5",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T16:53:07.010Z",
+ "finished_at": "2026-09-20T16:53:07.046Z",
+ "queued_at": "2026-09-20T16:53:06.719Z"
+ },
+ {
+ "model": "exo__qwen3-5-397b-a17b-8bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T16:53:07.082Z",
+ "finished_at": "2026-09-20T16:53:07.110Z",
+ "queued_at": "2026-09-20T16:53:06.744Z"
+ }
+ ]
+ },
+ {
+ "id": "81dc2bc5144a",
+ "title": "Demoscene Competition #21 — Slime Creature Terrarium",
+ "prompt": "Build this as one complete, self-contained HTML file: Gooey metaballs staged as a terrarium of glowing 'slime creatures' that merge and split; controls for count/threshold/palette, a cursor that repels them, and a snapshot button. 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": "Demoscene",
+ "designTools": false,
+ "created_at": "2026-09-20T16:58:14.948Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "exo__minimax-m2-7-5bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T16:58:15.295Z",
+ "finished_at": "2026-09-20T16:58:15.352Z",
+ "queued_at": "2026-09-20T16:58:15.015Z"
+ },
+ {
+ "model": "exo__qwen3-5-2b-mlx-8bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T16:58:15.395Z",
+ "finished_at": "2026-09-20T16:58:15.476Z",
+ "queued_at": "2026-09-20T16:58:15.057Z"
+ },
+ {
+ "model": "exo__deepseek-v3-2-8bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T16:58:15.545Z",
+ "finished_at": "2026-09-20T16:58:15.594Z",
+ "queued_at": "2026-09-20T16:58:15.113Z"
+ },
+ {
+ "model": "exo__qwen3-5-27b-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T16:58:15.643Z",
+ "finished_at": "2026-09-20T16:58:15.687Z",
+ "queued_at": "2026-09-20T16:58:15.157Z"
+ },
+ {
+ "model": "exo__gemma-4-e2b-it-8bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T16:58:15.721Z",
+ "finished_at": "2026-09-20T16:58:15.750Z",
+ "queued_at": "2026-09-20T16:58:15.199Z"
+ },
+ {
+ "model": "exo__qwen3-coder-next-5bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T16:58:15.776Z",
+ "finished_at": "2026-09-20T16:58:15.801Z",
+ "queued_at": "2026-09-20T16:58:15.243Z"
+ }
+ ]
}
]
\ No newline at end of file
diff --git a/yolo/arena-loop-state.json b/yolo/arena-loop-state.json
index 4de8d3c..8df1a40 100644
--- a/yolo/arena-loop-state.json
+++ b/yolo/arena-loop-state.json
@@ -1 +1 @@
-{"promptIdx":3,"modelOffset":10,"compCount":{"Art":42,"Culture":41,"News":41,"Political Cartoon":41,"Games":21,"Real Work":21,"Data Viz":21,"Science":21,"Music":21,"Sports":20,"History":20,"Nature & Space":20,"Comedy":20,"Demoscene":20,"Finance":20,"Design":20},"catIdx":9,"perCat":{"Art":1,"Culture":1,"News":1,"Political Cartoon":1,"Games":3,"Real Work":3,"Data Viz":3,"Science":3,"Music":3,"Sports":2,"History":2,"Nature & Space":2,"Comedy":2,"Demoscene":2,"Finance":2,"Design":2}}
\ No newline at end of file
+{"promptIdx":3,"modelOffset":40,"compCount":{"Art":42,"Culture":41,"News":41,"Political Cartoon":41,"Games":21,"Real Work":21,"Data Viz":21,"Science":21,"Music":21,"Sports":21,"History":21,"Nature & Space":21,"Comedy":21,"Demoscene":21,"Finance":20,"Design":20},"catIdx":14,"perCat":{"Art":1,"Culture":1,"News":1,"Political Cartoon":1,"Games":3,"Real Work":3,"Data Viz":3,"Science":3,"Music":3,"Sports":3,"History":3,"Nature & Space":3,"Comedy":3,"Demoscene":3,"Finance":2,"Design":2}}
\ No newline at end of file
diff --git a/yolo/daily-log.jsonl b/yolo/daily-log.jsonl
index 1302fec..7f31fda 100644
--- a/yolo/daily-log.jsonl
+++ b/yolo/daily-log.jsonl
@@ -464,3 +464,9 @@
{"ts":"2026-09-20T15:57:31.641Z","id":"98304bf68d0f","promptId":"pomodoro","category":"Real Work","title":"Real Work Competition #21 — Lighthouse Focus Timer","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
{"ts":"2026-09-20T16:02:39.895Z","id":"5b597c609675","promptId":"scatter","category":"Data Viz","title":"Data Viz Competition #21 — Planet Dating Show","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
{"ts":"2026-09-20T16:17:40.528Z","id":"df572406a0ac","promptId":"cell","category":"Science","title":"Science Competition #21 — Cell as a Factory-City","models":6,"done":1,"errored":5,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-20T16:32:41.347Z","id":"d444ce34af61","promptId":"audioviz","category":"Music","title":"Music Competition #21 — Skyline Audio Visualizer","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-20T16:37:49.766Z","id":"f9e65b23682d","promptId":"statcard","category":"Sports","title":"Sports Competition #21 — Holographic Stat Cards","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-20T16:42:58.074Z","id":"fb8c803c92a6","promptId":"artifact","category":"History","title":"History Competition #21 — Spotlit Relic Viewer","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-20T16:48:06.455Z","id":"bae9e031aca8","promptId":"weather","category":"Nature & Space","title":"Nature & Space Competition #21 — Shake-the-Snow-Globe Weather","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-20T16:53:14.777Z","id":"34edc5cb1b5f","promptId":"roast","category":"Comedy","title":"Comedy Competition #21 — Roast or Toast Campfire","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-20T16:58:23.327Z","id":"81dc2bc5144a","promptId":"metaballs","category":"Demoscene","title":"Demoscene Competition #21 — Slime Creature Terrarium","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
← a91f02a auto-data-snapshot: 2026-09-20T09:27:07 (3 data files) — dat
·
back to Model Arena
·
auto-data-snapshot: 2026-09-20T10:33:56 (3 data files) — dat 772e30e →