← back to Model Arena
auto-data-snapshot: 2026-09-20T18:25:19 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl
70d9acf11bcefe77bb92a0943eac4543e013f28d · 2026-09-20 18:27:57 -0700 · auto-commit-fleet
Files touched
M data/challenges.jsonM yolo/arena-loop-state.jsonM yolo/daily-log.jsonl
Diff
commit 70d9acf11bcefe77bb92a0943eac4543e013f28d
Author: auto-commit-fleet <steve@designerwallcoverings.com>
Date: Sun Sep 20 18:27:57 2026 -0700
auto-data-snapshot: 2026-09-20T18:25:19 (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 | 3 +
3 files changed, 224 insertions(+), 1 deletion(-)
diff --git a/data/challenges.json b/data/challenges.json
index a776074..b7e32c1 100644
--- a/data/challenges.json
+++ b/data/challenges.json
@@ -73006,5 +73006,225 @@
"queued_at": "2026-09-21T00:50:57.100Z"
}
]
+ },
+ {
+ "id": "70bf087163da",
+ "title": "Demoscene Competition #25 — Lava-Lamp Boot Screen",
+ "prompt": "Build this as one complete, self-contained HTML file: A demoscene plasma pretending to be a lava-lamp OS boot screen — fake loading messages scroll over palette-cycling plasma, a 'sync to beat' toggle pulses it, and an fps counter sits in the corner. Reduced-motion fallback. 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": "2026-09-21T00:56:05.190Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "exo__nvidia-nemotron-3-nano-30b-a3b-mlx-8bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T00:56:05.479Z",
+ "finished_at": "2026-09-21T00:56:05.597Z",
+ "queued_at": "2026-09-21T00:56:05.239Z"
+ },
+ {
+ "model": "exo__gemma-4-31b-it-8bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T00:56:05.634Z",
+ "finished_at": "2026-09-21T00:56:05.692Z",
+ "queued_at": "2026-09-21T00:56:05.274Z"
+ },
+ {
+ "model": "qwen3-14b",
+ "status": "done",
+ "error": null,
+ "seconds": 104,
+ "cost": 0,
+ "started_at": "2026-09-21T00:56:05.520Z",
+ "finished_at": "2026-09-21T00:57:50.033Z",
+ "queued_at": "2026-09-21T00:56:05.312Z",
+ "bytes": 6900,
+ "thumb": true,
+ "aiScore": null,
+ "aiReason": "judge failed: all vision panelists failed"
+ },
+ {
+ "model": "mlx__qwen3-30b-a3b-instruct-2507-4bit",
+ "status": "error",
+ "error": "timeout after 600s",
+ "seconds": 600,
+ "cost": null,
+ "started_at": "2026-09-21T00:56:05.557Z",
+ "finished_at": "2026-09-21T01:06:05.598Z",
+ "queued_at": "2026-09-21T00:56:05.346Z"
+ },
+ {
+ "model": "exo__minimax-m2-7-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T00:56:05.744Z",
+ "finished_at": "2026-09-21T00:56:05.786Z",
+ "queued_at": "2026-09-21T00:56:05.416Z"
+ },
+ {
+ "model": "qwen25-7b",
+ "status": "error",
+ "error": "ollama bad response: 503",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T00:57:50.066Z",
+ "finished_at": "2026-09-21T00:57:50.304Z",
+ "queued_at": "2026-09-21T00:56:05.451Z"
+ }
+ ],
+ "judging": false,
+ "aiPick": null,
+ "judged_at": "2026-09-21T01:06:05.795Z"
+ },
+ {
+ "id": "363074b6ac94",
+ "title": "Finance Competition #25 — 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": "2026-09-21T01:11:06.529Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "mlx__qwen3-next-80b-a3b-instruct-4bit",
+ "status": "error",
+ "error": "timeout after 600s",
+ "seconds": 600,
+ "cost": null,
+ "started_at": "2026-09-21T01:11:07.245Z",
+ "finished_at": "2026-09-21T01:21:07.500Z",
+ "queued_at": "2026-09-21T01:11:06.600Z"
+ },
+ {
+ "model": "exo__qwen3-coder-480b-a35b-instruct-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T01:11:07.346Z",
+ "finished_at": "2026-09-21T01:11:07.499Z",
+ "queued_at": "2026-09-21T01:11:06.736Z"
+ },
+ {
+ "model": "mac1__minicpm-v-latest",
+ "status": "error",
+ "error": "ollama bad response: 503",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T01:11:07.431Z",
+ "finished_at": "2026-09-21T01:11:07.709Z",
+ "queued_at": "2026-09-21T01:11:06.815Z"
+ },
+ {
+ "model": "exo__qwen3-5-122b-a10b-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T01:11:07.606Z",
+ "finished_at": "2026-09-21T01:11:07.925Z",
+ "queued_at": "2026-09-21T01:11:06.930Z"
+ },
+ {
+ "model": "mac1__qwen2-5vl-7b",
+ "status": "error",
+ "error": "ollama bad response: 503",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T01:11:07.830Z",
+ "finished_at": "2026-09-21T01:11:08.124Z",
+ "queued_at": "2026-09-21T01:11:07.035Z"
+ },
+ {
+ "model": "exo__gemma-4-26b-a4b-it-6bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T01:11:08.012Z",
+ "finished_at": "2026-09-21T01:11:08.227Z",
+ "queued_at": "2026-09-21T01:11:07.120Z"
+ }
+ ]
+ },
+ {
+ "id": "cba641d46609",
+ "title": "Design Competition #25 — 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": "2026-09-21T01:26:07.777Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "exo__qwen3-6-35b-a3b-bf16",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T01:26:08.020Z",
+ "finished_at": "2026-09-21T01:26:08.061Z",
+ "queued_at": "2026-09-21T01:26:07.816Z"
+ },
+ {
+ "model": "exo__qwen3-vl-4b-instruct-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T01:26:08.127Z",
+ "finished_at": "2026-09-21T01:26:08.155Z",
+ "queued_at": "2026-09-21T01:26:07.850Z"
+ },
+ {
+ "model": "exo__minimax-m2-7",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T01:26:08.214Z",
+ "finished_at": "2026-09-21T01:26:08.247Z",
+ "queued_at": "2026-09-21T01:26:07.888Z"
+ },
+ {
+ "model": "exo__llama-3-3-70b-instruct-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T01:26:08.362Z",
+ "finished_at": "2026-09-21T01:26:08.391Z",
+ "queued_at": "2026-09-21T01:26:07.926Z"
+ },
+ {
+ "model": "exo__gemma-4-e2b-it-bf16",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T01:26:08.438Z",
+ "finished_at": "2026-09-21T01:26:08.515Z",
+ "queued_at": "2026-09-21T01:26:07.949Z"
+ },
+ {
+ "model": "exo__qwen3-next-80b-a3b-instruct-8bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T01:26:08.540Z",
+ "finished_at": "2026-09-21T01:26:08.582Z",
+ "queued_at": "2026-09-21T01:26:07.977Z"
+ }
+ ]
}
]
\ No newline at end of file
diff --git a/yolo/arena-loop-state.json b/yolo/arena-loop-state.json
index 3c6dab7..4162abb 100644
--- a/yolo/arena-loop-state.json
+++ b/yolo/arena-loop-state.json
@@ -1 +1 @@
-{"promptIdx":3,"modelOffset":127,"compCount":{"Art":50,"Culture":49,"News":49,"Political Cartoon":49,"Games":25,"Real Work":25,"Data Viz":25,"Science":25,"Music":25,"Sports":25,"History":25,"Nature & Space":25,"Comedy":25,"Demoscene":24,"Finance":24,"Design":24},"catIdx":13,"perCat":{"Art":1,"Culture":1,"News":1,"Political Cartoon":1,"Games":1,"Real Work":1,"Data Viz":1,"Science":1,"Music":1,"Sports":1,"History":1,"Nature & Space":1,"Comedy":1,"Demoscene":3,"Finance":3,"Design":3}}
\ No newline at end of file
+{"promptIdx":3,"modelOffset":16,"compCount":{"Art":50,"Culture":49,"News":49,"Political Cartoon":49,"Games":25,"Real Work":25,"Data Viz":25,"Science":25,"Music":25,"Sports":25,"History":25,"Nature & Space":25,"Comedy":25,"Demoscene":25,"Finance":25,"Design":25},"catIdx":16,"perCat":{"Art":1,"Culture":1,"News":1,"Political Cartoon":1,"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 7c01144..1509592 100644
--- a/yolo/daily-log.jsonl
+++ b/yolo/daily-log.jsonl
@@ -549,3 +549,6 @@
{"ts":"2026-09-21T00:40:48.578Z","id":"49a744932689","promptId":"timeline-hist","category":"History","title":"History Competition #25 — Walk-Through Age of Invention","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
{"ts":"2026-09-21T00:45:56.853Z","id":"bb5317cd3c91","promptId":"starmap","category":"Nature & Space","title":"Nature & Space Competition #25 — Invent Your Own Constellations","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
{"ts":"2026-09-21T00:51:05.140Z","id":"144e9e0182fd","promptId":"meme","category":"Comedy","title":"Comedy Competition #25 — The Meme Generator That Fights Back","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-21T01:06:06.160Z","id":"70bf087163da","promptId":"plasma","category":"Demoscene","title":"Demoscene Competition #25 — Lava-Lamp Boot Screen","models":6,"done":1,"errored":5,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-21T01:21:07.710Z","id":"363074b6ac94","promptId":"portfolio","category":"Finance","title":"Finance Competition #25 — Galactic Exchange Portfolio","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-21T01:26:16.027Z","id":"cba641d46609","promptId":"components","category":"Design","title":"Design Competition #25 — Design System Safari","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
← 8e866cb auto-data-snapshot: 2026-09-20T17:51:28 (3 data files) — dat
·
back to Model Arena
·
auto-data-snapshot: 2026-09-20T18:59:45 (3 data files) — dat 83a628c →