← back to Model Arena
auto-data-snapshot: 2026-09-19T12:06:31 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl
816ea2f5d40afbe1dbe791ba79a98cc09edfcea5 · 2026-09-19 12:07:38 -0700 · auto-commit-fleet
Files touched
M data/challenges.jsonM yolo/arena-loop-state.jsonM yolo/daily-log.jsonl
Diff
commit 816ea2f5d40afbe1dbe791ba79a98cc09edfcea5
Author: auto-commit-fleet <steve@designerwallcoverings.com>
Date: Sat Sep 19 12:07:38 2026 -0700
auto-data-snapshot: 2026-09-19T12:06:31 (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 1e381f2..543ff5e 100644
--- a/data/challenges.json
+++ b/data/challenges.json
@@ -51596,12 +51596,12 @@
"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": "2026-09-19T18:29:19.558Z",
- "finished_at": null,
+ "finished_at": "2026-09-19T18:39:19.615Z",
"queued_at": "2026-09-19T18:29:19.451Z"
},
{
@@ -51655,5 +51655,360 @@
"queued_at": "2026-09-19T18:29:19.541Z"
}
]
+ },
+ {
+ "id": "831d7e26bd93",
+ "title": "Finance Competition #10 — Galactic Exchange Portfolio",
+ "prompt": "Build this as one complete, self-contained HTML file: A portfolio tracker for an INVENTED galactic exchange (holdings in 'moon deeds' and 'comet futures'): allocation donut as a planet system, a gain/loss aura, a sortable table, and a what-if rebalance slider that re-orbits everything. 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": "Finance",
+ "designTools": false,
+ "created_at": "2026-09-19T18:44:19.894Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "exo__qwen3-6-35b-a3b-bf16",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T18:44:20.050Z",
+ "finished_at": "2026-09-19T18:44:20.090Z",
+ "queued_at": "2026-09-19T18:44:19.927Z"
+ },
+ {
+ "model": "exo__qwen3-vl-4b-instruct-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T18:44:20.107Z",
+ "finished_at": "2026-09-19T18:44:20.143Z",
+ "queued_at": "2026-09-19T18:44:19.948Z"
+ },
+ {
+ "model": "exo__minimax-m2-7",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T18:44:20.162Z",
+ "finished_at": "2026-09-19T18:44:20.183Z",
+ "queued_at": "2026-09-19T18:44:19.969Z"
+ },
+ {
+ "model": "exo__llama-3-3-70b-instruct-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T18:44:20.201Z",
+ "finished_at": "2026-09-19T18:44:20.224Z",
+ "queued_at": "2026-09-19T18:44:19.988Z"
+ },
+ {
+ "model": "exo__gemma-4-e2b-it-bf16",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T18:44:20.249Z",
+ "finished_at": "2026-09-19T18:44:20.270Z",
+ "queued_at": "2026-09-19T18:44:20.012Z"
+ },
+ {
+ "model": "exo__qwen3-next-80b-a3b-instruct-8bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T18:44:20.286Z",
+ "finished_at": "2026-09-19T18:44:20.310Z",
+ "queued_at": "2026-09-19T18:44:20.032Z"
+ }
+ ]
+ },
+ {
+ "id": "abd5fe4d7d3b",
+ "title": "Design Competition #10 — Design System Safari",
+ "prompt": "Build this as one complete, self-contained HTML file: A UI component kit staged as a 'design system safari' — each component (buttons, inputs, tabs, modal, toast, cards) lives in a themed habitat card, a live light/dark toggle changes the biome, and every accessible state is shown. 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": "Design",
+ "designTools": false,
+ "created_at": "2026-09-19T18:49:28.095Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "exo__qwen3-6-27b-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T18:49:28.318Z",
+ "finished_at": "2026-09-19T18:49:28.371Z",
+ "queued_at": "2026-09-19T18:49:28.132Z"
+ },
+ {
+ "model": "exo__glm-4-7-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T18:49:28.391Z",
+ "finished_at": "2026-09-19T18:49:28.417Z",
+ "queued_at": "2026-09-19T18:49:28.180Z"
+ },
+ {
+ "model": "exo__gemma-4-31b-it-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T18:49:28.436Z",
+ "finished_at": "2026-09-19T18:49:28.459Z",
+ "queued_at": "2026-09-19T18:49:28.216Z"
+ },
+ {
+ "model": "exo__nvidia-nemotron-3-nano-30b-a3b-mlx-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T18:49:28.479Z",
+ "finished_at": "2026-09-19T18:49:28.512Z",
+ "queued_at": "2026-09-19T18:49:28.240Z"
+ },
+ {
+ "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": "2026-09-19T18:49:28.543Z",
+ "finished_at": "2026-09-19T18:49:28.580Z",
+ "queued_at": "2026-09-19T18:49:28.266Z"
+ },
+ {
+ "model": "exo__qwen3-coder-next-6bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T18:49:28.601Z",
+ "finished_at": "2026-09-19T18:49:28.627Z",
+ "queued_at": "2026-09-19T18:49:28.289Z"
+ }
+ ]
+ },
+ {
+ "id": "e4e17811e2ab",
+ "title": "Art Competition #21 — Deep-Sea Fractal Dive",
+ "prompt": "Build this as one complete, self-contained HTML file: A fractal explorer disguised as a deep-sea dive: descend into a Julia set as if sinking through bioluminescent water, a depth gauge ticking, the palette cooling with depth, and a 'creature spotted' note at interesting zoom levels. 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": "Art",
+ "designTools": false,
+ "created_at": "2026-09-19T18:54:36.359Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "exo__step-3-5-flash-6bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T18:54:36.578Z",
+ "finished_at": "2026-09-19T18:54:36.600Z",
+ "queued_at": "2026-09-19T18:54:36.389Z"
+ },
+ {
+ "model": "exo__qwen3-next-80b-a3b-thinking-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T18:54:36.617Z",
+ "finished_at": "2026-09-19T18:54:36.638Z",
+ "queued_at": "2026-09-19T18:54:36.423Z"
+ },
+ {
+ "model": "exo__deepseek-v3-1-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T18:54:36.660Z",
+ "finished_at": "2026-09-19T18:54:36.684Z",
+ "queued_at": "2026-09-19T18:54:36.459Z"
+ },
+ {
+ "model": "exo__llama-3-1-nemotron-70b-instruct-hf-8bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T18:54:36.701Z",
+ "finished_at": "2026-09-19T18:54:36.721Z",
+ "queued_at": "2026-09-19T18:54:36.492Z"
+ },
+ {
+ "model": "exo__gemma-4-e4b-it-6bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T18:54:36.741Z",
+ "finished_at": "2026-09-19T18:54:36.763Z",
+ "queued_at": "2026-09-19T18:54:36.523Z"
+ },
+ {
+ "model": "exo__nvidia-nemotron-3-nano-30b-a3b-mlx-5bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T18:54:36.784Z",
+ "finished_at": "2026-09-19T18:54:36.805Z",
+ "queued_at": "2026-09-19T18:54:36.551Z"
+ }
+ ]
+ },
+ {
+ "id": "c918c3110575",
+ "title": "Culture Competition #20 — Lantern Temple by Night",
+ "prompt": "Build this as one complete, self-contained HTML file: A candle-lit scrollytelling tour of an INVENTED heritage temple where scrolling moves a lantern's glow across carvings, revealing a story chapter by chapter, and a constellation completes at the end. 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": "Culture",
+ "designTools": false,
+ "created_at": "2026-09-19T18:59:44.822Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "exo__glm-4-7-flash-6bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T18:59:45.037Z",
+ "finished_at": "2026-09-19T18:59:45.080Z",
+ "queued_at": "2026-09-19T18:59:44.853Z"
+ },
+ {
+ "model": "exo__qwen3-5-35b-a3b-8bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T18:59:45.117Z",
+ "finished_at": "2026-09-19T18:59:45.179Z",
+ "queued_at": "2026-09-19T18:59:44.886Z"
+ },
+ {
+ "model": "exo__glm-4-7-8bit-gs32",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T18:59:45.217Z",
+ "finished_at": "2026-09-19T18:59:45.258Z",
+ "queued_at": "2026-09-19T18:59:44.922Z"
+ },
+ {
+ "model": "exo__glm-5-1",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T18:59:45.294Z",
+ "finished_at": "2026-09-19T18:59:45.337Z",
+ "queued_at": "2026-09-19T18:59:44.955Z"
+ },
+ {
+ "model": "exo__kimi-k2-5",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T18:59:45.366Z",
+ "finished_at": "2026-09-19T18:59:45.403Z",
+ "queued_at": "2026-09-19T18:59:44.982Z"
+ },
+ {
+ "model": "exo__qwen3-5-397b-a17b-8bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T18:59:45.422Z",
+ "finished_at": "2026-09-19T18:59:45.446Z",
+ "queued_at": "2026-09-19T18:59:45.008Z"
+ }
+ ]
+ },
+ {
+ "id": "d82ee5b38daf",
+ "title": "News Competition #20 — The City That Floods As You Scroll",
+ "prompt": "Build this as one complete, self-contained HTML file: A data-journalism scrollytelling piece where an INVENTED city floods frame by frame as you drag a rising-sea slider, annotated charts surface, and a final interaction lets the reader 'plant' defenses and watch the chart bend. 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": "News",
+ "designTools": false,
+ "created_at": "2026-09-19T19:04:53.073Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "exo__minimax-m2-7-5bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T19:04:53.256Z",
+ "finished_at": "2026-09-19T19:04:53.275Z",
+ "queued_at": "2026-09-19T19:04:53.102Z"
+ },
+ {
+ "model": "exo__qwen3-5-2b-mlx-8bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T19:04:53.291Z",
+ "finished_at": "2026-09-19T19:04:53.309Z",
+ "queued_at": "2026-09-19T19:04:53.138Z"
+ },
+ {
+ "model": "exo__deepseek-v3-2-8bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T19:04:53.340Z",
+ "finished_at": "2026-09-19T19:04:53.361Z",
+ "queued_at": "2026-09-19T19:04:53.164Z"
+ },
+ {
+ "model": "exo__qwen3-5-27b-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T19:04:53.378Z",
+ "finished_at": "2026-09-19T19:04:53.397Z",
+ "queued_at": "2026-09-19T19:04:53.188Z"
+ },
+ {
+ "model": "exo__gemma-4-e2b-it-8bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T19:04:53.412Z",
+ "finished_at": "2026-09-19T19:04:53.430Z",
+ "queued_at": "2026-09-19T19:04:53.215Z"
+ },
+ {
+ "model": "exo__qwen3-coder-next-5bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T19:04:53.445Z",
+ "finished_at": "2026-09-19T19:04:53.463Z",
+ "queued_at": "2026-09-19T19:04:53.236Z"
+ }
+ ]
}
]
\ No newline at end of file
diff --git a/yolo/arena-loop-state.json b/yolo/arena-loop-state.json
index 0b65821..435faa0 100644
--- a/yolo/arena-loop-state.json
+++ b/yolo/arena-loop-state.json
@@ -1 +1 @@
-{"promptIdx":3,"modelOffset":10,"compCount":{"Art":20,"Culture":19,"News":19,"Political Cartoon":19,"Games":10,"Real Work":10,"Data Viz":10,"Science":10,"Music":10,"Sports":10,"History":10,"Nature & Space":10,"Comedy":10,"Demoscene":10,"Finance":9,"Design":9},"catIdx":14,"perCat":{"Art":3,"Culture":3,"News":3,"Political Cartoon":3,"Games":1,"Real Work":1,"Data Viz":1,"Science":1,"Music":1,"Sports":1,"History":1,"Nature & Space":1,"Comedy":1,"Demoscene":1,"Finance":3,"Design":3}}
\ No newline at end of file
+{"promptIdx":3,"modelOffset":40,"compCount":{"Art":21,"Culture":20,"News":20,"Political Cartoon":19,"Games":10,"Real Work":10,"Data Viz":10,"Science":10,"Music":10,"Sports":10,"History":10,"Nature & Space":10,"Comedy":10,"Demoscene":10,"Finance":10,"Design":10},"catIdx":19,"perCat":{"Art":4,"Culture":4,"News":4,"Political Cartoon":3,"Games":1,"Real Work":1,"Data Viz":1,"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
diff --git a/yolo/daily-log.jsonl b/yolo/daily-log.jsonl
index 558fc43..c4669a5 100644
--- a/yolo/daily-log.jsonl
+++ b/yolo/daily-log.jsonl
@@ -248,3 +248,9 @@
{"ts":"2026-09-19T18:04:10.255Z","id":"a3937ade5395","promptId":"timeline-hist","category":"History","title":"History Competition #10 — Walk-Through Age of Invention","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
{"ts":"2026-09-19T18:09:18.404Z","id":"8f8bd775561d","promptId":"starmap","category":"Nature & Space","title":"Nature & Space Competition #10 — Invent Your Own Constellations","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
{"ts":"2026-09-19T18:24:19.369Z","id":"4c1635200597","promptId":"meme","category":"Comedy","title":"Comedy Competition #10 — The Meme Generator That Fights Back","models":6,"done":1,"errored":5,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-19T18:39:19.850Z","id":"1752d724993b","promptId":"plasma","category":"Demoscene","title":"Demoscene Competition #10 — Lava-Lamp Boot Screen","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-19T18:44:28.055Z","id":"831d7e26bd93","promptId":"portfolio","category":"Finance","title":"Finance Competition #10 — Galactic Exchange Portfolio","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-19T18:49:36.321Z","id":"abd5fe4d7d3b","promptId":"components","category":"Design","title":"Design Competition #10 — Design System Safari","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-19T18:54:44.581Z","id":"e4e17811e2ab","promptId":"fractal","category":"Art","title":"Art Competition #21 — Deep-Sea Fractal Dive","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-19T18:59:53.041Z","id":"c918c3110575","promptId":"heritage","category":"Culture","title":"Culture Competition #20 — Lantern Temple by Night","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-19T19:05:01.260Z","id":"d82ee5b38daf","promptId":"climate-story","category":"News","title":"News Competition #20 — The City That Floods As You Scroll","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
← 14bb2d8 auto-data-snapshot: 2026-09-19T11:34:41 (3 data files) — dat
·
back to Model Arena
·
auto-data-snapshot: 2026-09-19T12:38:08 (3 data files) — dat b1f3085 →