← back to Model Arena
auto-data-snapshot: 2026-09-20T11:40:52 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl
c2fd688a8b67d268be9b61cf37f0cb67a77c6e3c · 2026-09-20 11:43:54 -0700 · auto-commit-fleet
Files touched
M data/challenges.jsonM yolo/arena-loop-state.jsonM yolo/daily-log.jsonl
Diff
commit c2fd688a8b67d268be9b61cf37f0cb67a77c6e3c
Author: auto-commit-fleet <steve@designerwallcoverings.com>
Date: Sun Sep 20 11:43:54 2026 -0700
auto-data-snapshot: 2026-09-20T11:40:52 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl
---
data/challenges.json | 220 +++++++++++++++++++++++++++++++++++++++++++++
yolo/arena-loop-state.json | 2 +-
yolo/daily-log.jsonl | 2 +
3 files changed, 223 insertions(+), 1 deletion(-)
diff --git a/data/challenges.json b/data/challenges.json
index 1f48f37..2178b02 100644
--- a/data/challenges.json
+++ b/data/challenges.json
@@ -68299,5 +68299,225 @@
"queued_at": "2026-09-20T18:05:03.873Z"
}
]
+ },
+ {
+ "id": "698740aff0ea",
+ "title": "Science Competition #22 — 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": "2026-09-20T18:10:11.937Z",
+ "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": "2026-09-20T18:10:12.142Z",
+ "finished_at": "2026-09-20T18:10:12.177Z",
+ "queued_at": "2026-09-20T18:10:11.969Z"
+ },
+ {
+ "model": "exo__deepseek-v4-flash",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T18:10:12.205Z",
+ "finished_at": "2026-09-20T18:10:12.240Z",
+ "queued_at": "2026-09-20T18:10:12.002Z"
+ },
+ {
+ "model": "exo__qwen3-next-80b-a3b-thinking-8bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T18:10:12.278Z",
+ "finished_at": "2026-09-20T18:10:12.315Z",
+ "queued_at": "2026-09-20T18:10:12.047Z"
+ },
+ {
+ "model": "exo__deepseek-v4-pro",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T18:10:12.337Z",
+ "finished_at": "2026-09-20T18:10:12.362Z",
+ "queued_at": "2026-09-20T18:10:12.072Z"
+ },
+ {
+ "model": "exo__deepseek-v3-1-8bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T18:10:12.385Z",
+ "finished_at": "2026-09-20T18:10:12.420Z",
+ "queued_at": "2026-09-20T18:10:12.095Z"
+ },
+ {
+ "model": "exo__glm-5-8bit-mxfp8",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T18:10:12.441Z",
+ "finished_at": "2026-09-20T18:10:12.466Z",
+ "queued_at": "2026-09-20T18:10:12.117Z"
+ }
+ ]
+ },
+ {
+ "id": "fcdd1832040c",
+ "title": "Music Competition #22 — 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": "2026-09-20T18:15:20.222Z",
+ "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": "2026-09-20T18:15:20.440Z",
+ "finished_at": "2026-09-20T18:15:20.501Z",
+ "queued_at": "2026-09-20T18:15:20.259Z"
+ },
+ {
+ "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": "2026-09-20T18:15:20.535Z",
+ "finished_at": "2026-09-20T18:15:20.585Z",
+ "queued_at": "2026-09-20T18:15:20.294Z"
+ },
+ {
+ "model": "exo__kimi-k2-6",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T18:15:20.613Z",
+ "finished_at": "2026-09-20T18:15:20.641Z",
+ "queued_at": "2026-09-20T18:15:20.329Z"
+ },
+ {
+ "model": "exo__nvidia-nemotron-3-nano-30b-a3b-mlx-8bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T18:15:20.670Z",
+ "finished_at": "2026-09-20T18:15:20.700Z",
+ "queued_at": "2026-09-20T18:15:20.363Z"
+ },
+ {
+ "model": "exo__gemma-4-31b-it-8bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T18:15:20.727Z",
+ "finished_at": "2026-09-20T18:15:20.767Z",
+ "queued_at": "2026-09-20T18:15:20.386Z"
+ },
+ {
+ "model": "qwen3-14b",
+ "status": "done",
+ "error": null,
+ "seconds": 255,
+ "cost": 0,
+ "started_at": "2026-09-20T18:15:20.469Z",
+ "finished_at": "2026-09-20T18:19:35.442Z",
+ "queued_at": "2026-09-20T18:15:20.410Z",
+ "bytes": 15292,
+ "thumb": true,
+ "aiScore": null,
+ "aiReason": "judge failed: all vision panelists failed"
+ }
+ ],
+ "judging": false,
+ "aiPick": null,
+ "judged_at": "2026-09-20T18:19:37.773Z"
+ },
+ {
+ "id": "17adb144aa1f",
+ "title": "Sports Competition #22 — 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": "2026-09-20T18:24:36.717Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "mlx__qwen3-30b-a3b-instruct-2507-4bit",
+ "status": "error",
+ "error": "timeout after 600s",
+ "seconds": 600,
+ "cost": null,
+ "started_at": "2026-09-20T18:24:36.884Z",
+ "finished_at": "2026-09-20T18:34:36.971Z",
+ "queued_at": "2026-09-20T18:24:36.745Z"
+ },
+ {
+ "model": "exo__minimax-m2-7-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T18:24:36.906Z",
+ "finished_at": "2026-09-20T18:24:36.976Z",
+ "queued_at": "2026-09-20T18:24:36.772Z"
+ },
+ {
+ "model": "qwen25-7b",
+ "status": "error",
+ "error": "ollama bad response: 503",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T18:24:36.935Z",
+ "finished_at": "2026-09-20T18:24:37.134Z",
+ "queued_at": "2026-09-20T18:24:36.794Z"
+ },
+ {
+ "model": "mlx__qwen3-next-80b-a3b-instruct-4bit",
+ "status": "running",
+ "error": null,
+ "seconds": null,
+ "cost": null,
+ "started_at": "2026-09-20T18:34:37.024Z",
+ "finished_at": null,
+ "queued_at": "2026-09-20T18:24:36.817Z"
+ },
+ {
+ "model": "exo__qwen3-coder-480b-a35b-instruct-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T18:24:37.036Z",
+ "finished_at": "2026-09-20T18:24:37.079Z",
+ "queued_at": "2026-09-20T18:24:36.840Z"
+ },
+ {
+ "model": "mac1__minicpm-v-latest",
+ "status": "error",
+ "error": "ollama bad response: 503",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T18:24:37.179Z",
+ "finished_at": "2026-09-20T18:24:37.340Z",
+ "queued_at": "2026-09-20T18:24:36.861Z"
+ }
+ ]
}
]
\ No newline at end of file
diff --git a/yolo/arena-loop-state.json b/yolo/arena-loop-state.json
index c188dba..a972c1c 100644
--- a/yolo/arena-loop-state.json
+++ b/yolo/arena-loop-state.json
@@ -1 +1 @@
-{"promptIdx":3,"modelOffset":118,"compCount":{"Art":44,"Culture":43,"News":43,"Political Cartoon":43,"Games":22,"Real Work":22,"Data Viz":22,"Science":21,"Music":21,"Sports":21,"History":21,"Nature & Space":21,"Comedy":21,"Demoscene":21,"Finance":21,"Design":21},"catIdx":7,"perCat":{"Art":3,"Culture":3,"News":3,"Political Cartoon":3,"Games":1,"Real Work":1,"Data Viz":1,"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":44,"Culture":43,"News":43,"Political Cartoon":43,"Games":22,"Real Work":22,"Data Viz":22,"Science":22,"Music":22,"Sports":22,"History":21,"Nature & Space":21,"Comedy":21,"Demoscene":21,"Finance":21,"Design":21},"catIdx":10,"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":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 b3108d8..1614e1c 100644
--- a/yolo/daily-log.jsonl
+++ b/yolo/daily-log.jsonl
@@ -483,3 +483,5 @@
{"ts":"2026-09-20T17:54:55.333Z","id":"29370a92aa56","promptId":"snake","category":"Games","title":"Games Competition #22 — Comet Snake in a Dying Galaxy","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
{"ts":"2026-09-20T18:00:03.673Z","id":"632e0ba0c57f","promptId":"crm","category":"Real Work","title":"Real Work Competition #22 — Fishing-Dock CRM","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
{"ts":"2026-09-20T18:05:11.906Z","id":"669ddeb23cde","promptId":"multi-chart","category":"Data Viz","title":"Data Viz Competition #22 — City of Data Dashboard","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-20T18:10:20.145Z","id":"698740aff0ea","promptId":"solar","category":"Science","title":"Science Competition #22 — Conduct the Solar System","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-20T18:19:36.640Z","id":"fcdd1832040c","promptId":"sequencer","category":"Music","title":"Music Competition #22 — Constellation Sequencer","models":6,"done":1,"errored":5,"settled":true,"aiPick":null,"loop":true}
← 026b871 auto-data-snapshot: 2026-09-20T11:06:41 (3 data files) — dat
·
back to Model Arena
·
auto-data-snapshot: 2026-09-20T12:15:15 (3 data files) — dat cea9fea →