← back to Model Arena
auto-data-snapshot: 2026-09-19T04:40:20 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl
a0f5d395917f021746c4499bbace02767cd8e8ac · 2026-09-19 04:41:38 -0700 · auto-commit-fleet
Files touched
M data/challenges.jsonM yolo/arena-loop-state.jsonM yolo/daily-log.jsonl
Diff
commit a0f5d395917f021746c4499bbace02767cd8e8ac
Author: auto-commit-fleet <steve@designerwallcoverings.com>
Date: Sat Sep 19 04:41:38 2026 -0700
auto-data-snapshot: 2026-09-19T04:40:20 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl
---
data/challenges.json | 295 +++++++++++++++++++++++++++++++++++++++++++++
yolo/arena-loop-state.json | 2 +-
yolo/daily-log.jsonl | 3 +
3 files changed, 299 insertions(+), 1 deletion(-)
diff --git a/data/challenges.json b/data/challenges.json
index 6e6b93d..9336db3 100644
--- a/data/challenges.json
+++ b/data/challenges.json
@@ -46672,5 +46672,300 @@
"queued_at": "2026-09-19T11:07:05.155Z"
}
]
+ },
+ {
+ "id": "002e11f046ea",
+ "title": "Real Work Competition #7 — Fishing-Dock CRM",
+ "prompt": "Build this as one complete, self-contained HTML file: A CRM where each lead is a fish on a line you drag between stages (Nibble -> Hooked -> Landed), per-stage totals shown as a catch tally, with search, quick-add, and validation. Playful but genuinely usable. 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": "Real Work",
+ "designTools": false,
+ "created_at": "2026-09-19T11:12:13.237Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "exo__glm-5-1-mxfp4-q8",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T11:12:13.518Z",
+ "finished_at": "2026-09-19T11:12:13.559Z",
+ "queued_at": "2026-09-19T11:12:13.269Z"
+ },
+ {
+ "model": "exo__qwen3-coder-480b-a35b-instruct-8bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T11:12:13.593Z",
+ "finished_at": "2026-09-19T11:12:13.646Z",
+ "queued_at": "2026-09-19T11:12:13.291Z"
+ },
+ {
+ "model": "exo__minimax-m2-5-6bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T11:12:13.700Z",
+ "finished_at": "2026-09-19T11:12:13.751Z",
+ "queued_at": "2026-09-19T11:12:13.329Z"
+ },
+ {
+ "model": "exo__minimax-m2-7-8bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T11:12:13.792Z",
+ "finished_at": "2026-09-19T11:12:13.880Z",
+ "queued_at": "2026-09-19T11:12:13.360Z"
+ },
+ {
+ "model": "exo__qwen3-5-122b-a10b-8bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T11:12:14.013Z",
+ "finished_at": "2026-09-19T11:12:14.068Z",
+ "queued_at": "2026-09-19T11:12:13.439Z"
+ },
+ {
+ "model": "exo__kimi-k2-instruct-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T11:12:14.104Z",
+ "finished_at": "2026-09-19T11:12:14.132Z",
+ "queued_at": "2026-09-19T11:12:13.479Z"
+ }
+ ]
+ },
+ {
+ "id": "1e16cf3734db",
+ "title": "Data Viz Competition #7 — 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": "2026-09-19T11:17:21.572Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "exo__llama-3-1-nemotron-70b-instruct-hf-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T11:17:21.758Z",
+ "finished_at": "2026-09-19T11:17:21.812Z",
+ "queued_at": "2026-09-19T11:17:21.605Z"
+ },
+ {
+ "model": "exo__deepseek-v4-flash",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T11:17:21.840Z",
+ "finished_at": "2026-09-19T11:17:21.879Z",
+ "queued_at": "2026-09-19T11:17:21.638Z"
+ },
+ {
+ "model": "exo__qwen3-next-80b-a3b-thinking-8bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T11:17:21.912Z",
+ "finished_at": "2026-09-19T11:17:21.942Z",
+ "queued_at": "2026-09-19T11:17:21.659Z"
+ },
+ {
+ "model": "exo__deepseek-v4-pro",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T11:17:21.965Z",
+ "finished_at": "2026-09-19T11:17:22.023Z",
+ "queued_at": "2026-09-19T11:17:21.678Z"
+ },
+ {
+ "model": "exo__deepseek-v3-1-8bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T11:17:22.079Z",
+ "finished_at": "2026-09-19T11:17:22.142Z",
+ "queued_at": "2026-09-19T11:17:21.707Z"
+ },
+ {
+ "model": "exo__glm-5-8bit-mxfp8",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T11:17:22.197Z",
+ "finished_at": "2026-09-19T11:17:22.239Z",
+ "queued_at": "2026-09-19T11:17:21.731Z"
+ }
+ ]
+ },
+ {
+ "id": "efb1652c2a4f",
+ "title": "Science Competition #7 — 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": "2026-09-19T11:22:29.803Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "exo__nvidia-nemotron-3-nano-30b-a3b-mlx-mxfp4",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T11:22:29.971Z",
+ "finished_at": "2026-09-19T11:22:30.031Z",
+ "queued_at": "2026-09-19T11:22:29.838Z"
+ },
+ {
+ "model": "exo__llama-3-1-nemotron-nano-4b-v1-1-8bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T11:22:30.053Z",
+ "finished_at": "2026-09-19T11:22:30.082Z",
+ "queued_at": "2026-09-19T11:22:29.863Z"
+ },
+ {
+ "model": "exo__kimi-k2-6",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T11:22:30.105Z",
+ "finished_at": "2026-09-19T11:22:30.138Z",
+ "queued_at": "2026-09-19T11:22:29.884Z"
+ },
+ {
+ "model": "exo__nvidia-nemotron-3-nano-30b-a3b-mlx-8bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T11:22:30.157Z",
+ "finished_at": "2026-09-19T11:22:30.180Z",
+ "queued_at": "2026-09-19T11:22:29.904Z"
+ },
+ {
+ "model": "exo__gemma-4-31b-it-8bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T11:22:30.195Z",
+ "finished_at": "2026-09-19T11:22:30.217Z",
+ "queued_at": "2026-09-19T11:22:29.928Z"
+ },
+ {
+ "model": "qwen3-14b",
+ "status": "done",
+ "error": null,
+ "seconds": 128,
+ "cost": 0,
+ "started_at": "2026-09-19T11:22:29.998Z",
+ "finished_at": "2026-09-19T11:24:38.123Z",
+ "queued_at": "2026-09-19T11:22:29.950Z",
+ "bytes": 8194,
+ "thumb": true,
+ "aiScore": null,
+ "aiReason": "judge failed: all vision panelists failed"
+ }
+ ],
+ "judging": false,
+ "aiPick": null,
+ "judged_at": "2026-09-19T11:24:40.336Z"
+ },
+ {
+ "id": "abcdb201ed45",
+ "title": "Music Competition #7 — 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": "2026-09-19T11:29:38.223Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "mlx__qwen3-30b-a3b-instruct-2507-4bit",
+ "status": "error",
+ "error": "timeout after 600s",
+ "seconds": 600,
+ "cost": null,
+ "started_at": "2026-09-19T11:29:38.718Z",
+ "finished_at": "2026-09-19T11:39:38.930Z",
+ "queued_at": "2026-09-19T11:29:38.279Z"
+ },
+ {
+ "model": "exo__minimax-m2-7-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T11:29:38.781Z",
+ "finished_at": "2026-09-19T11:29:39.101Z",
+ "queued_at": "2026-09-19T11:29:38.399Z"
+ },
+ {
+ "model": "qwen25-7b",
+ "status": "done",
+ "error": null,
+ "seconds": 43,
+ "cost": 0,
+ "started_at": "2026-09-19T11:29:38.849Z",
+ "finished_at": "2026-09-19T11:30:22.393Z",
+ "queued_at": "2026-09-19T11:29:38.457Z",
+ "bytes": 4603,
+ "thumb": true
+ },
+ {
+ "model": "mlx__qwen3-next-80b-a3b-instruct-4bit",
+ "status": "running",
+ "error": null,
+ "seconds": null,
+ "cost": null,
+ "started_at": "2026-09-19T11:39:38.979Z",
+ "finished_at": null,
+ "queued_at": "2026-09-19T11:29:38.526Z"
+ },
+ {
+ "model": "exo__qwen3-coder-480b-a35b-instruct-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T11:29:39.157Z",
+ "finished_at": "2026-09-19T11:29:39.700Z",
+ "queued_at": "2026-09-19T11:29:38.604Z"
+ },
+ {
+ "model": "mac1__minicpm-v-latest",
+ "status": "done",
+ "error": null,
+ "seconds": 12,
+ "cost": 0,
+ "started_at": "2026-09-19T11:30:22.418Z",
+ "finished_at": "2026-09-19T11:30:34.748Z",
+ "queued_at": "2026-09-19T11:29:38.661Z",
+ "bytes": 931,
+ "thumb": true
+ }
+ ]
}
]
\ No newline at end of file
diff --git a/yolo/arena-loop-state.json b/yolo/arena-loop-state.json
index b1e650b..1442350 100644
--- a/yolo/arena-loop-state.json
+++ b/yolo/arena-loop-state.json
@@ -1 +1 @@
-{"promptIdx":3,"modelOffset":112,"compCount":{"Art":14,"Culture":13,"News":13,"Political Cartoon":13,"Games":7,"Real Work":6,"Data Viz":6,"Science":6,"Music":6,"Sports":6,"History":6,"Nature & Space":6,"Comedy":6,"Demoscene":6,"Finance":6,"Design":6},"catIdx":5,"perCat":{"Art":1,"Culture":1,"News":1,"Political Cartoon":1,"Games":1,"Real Work":3,"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":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
diff --git a/yolo/daily-log.jsonl b/yolo/daily-log.jsonl
index aa9eb10..b03e797 100644
--- a/yolo/daily-log.jsonl
+++ b/yolo/daily-log.jsonl
@@ -179,3 +179,6 @@
{"ts":"2026-09-19T10:56:56.513Z","id":"5f1db2d62e4b","promptId":"election-viz","category":"News","title":"News Competition #13 — Election Night: Floating Isles","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
{"ts":"2026-09-19T11:02:04.734Z","id":"7999d780a7a7","promptId":"editorial-cartoon","category":"Political Cartoon","title":"Political Cartoon Competition #13 — The Seesaw Debate","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
{"ts":"2026-09-19T11:07:13.195Z","id":"bc08a1fe154b","promptId":"snake","category":"Games","title":"Games Competition #7 — Comet Snake in a Dying Galaxy","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
+{"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}
← 1264aec auto-data-snapshot: 2026-09-19T04:08:51 (3 data files) — dat
·
back to Model Arena
·
auto-data-snapshot: 2026-09-19T05:12:50 (3 data files) — dat e99ddc8 →