← back to Model Arena
auto-data-snapshot: 2026-09-19T17:56:16 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl
537ce89aa248e6741887fb605ef3090664d92950 · 2026-09-19 17:57:26 -0700 · auto-commit-fleet
Files touched
M data/challenges.jsonM yolo/arena-loop-state.jsonM yolo/daily-log.jsonl
Diff
commit 537ce89aa248e6741887fb605ef3090664d92950
Author: auto-commit-fleet <steve@designerwallcoverings.com>
Date: Sat Sep 19 17:57:26 2026 -0700
auto-data-snapshot: 2026-09-19T17:56:16 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl
---
data/challenges.json | 362 +++++++++++++++++++++++++++++++++++++++++++++
yolo/arena-loop-state.json | 2 +-
yolo/daily-log.jsonl | 4 +
3 files changed, 367 insertions(+), 1 deletion(-)
diff --git a/data/challenges.json b/data/challenges.json
index 7724ae6..e50eeae 100644
--- a/data/challenges.json
+++ b/data/challenges.json
@@ -55858,5 +55858,367 @@
"queued_at": "2026-09-20T00:23:37.572Z"
}
]
+ },
+ {
+ "id": "bdffa2e51ea4",
+ "title": "Demoscene Competition #13 — 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": "2026-09-20T00:28:45.675Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "exo__qwen3-5-397b-a17b-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T00:28:45.945Z",
+ "finished_at": "2026-09-20T00:28:45.982Z",
+ "queued_at": "2026-09-20T00:28:45.720Z"
+ },
+ {
+ "model": "exo__glm-4-5-air-bf16",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T00:28:46.022Z",
+ "finished_at": "2026-09-20T00:28:46.064Z",
+ "queued_at": "2026-09-20T00:28:45.760Z"
+ },
+ {
+ "model": "exo__qwen3-next-80b-a3b-instruct-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T00:28:46.103Z",
+ "finished_at": "2026-09-20T00:28:46.141Z",
+ "queued_at": "2026-09-20T00:28:45.794Z"
+ },
+ {
+ "model": "exo__nvidia-nemotron-3-nano-30b-a3b-nvfp4",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T00:28:46.172Z",
+ "finished_at": "2026-09-20T00:28:46.220Z",
+ "queued_at": "2026-09-20T00:28:45.828Z"
+ },
+ {
+ "model": "exo__qwen3-6-27b-8bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T00:28:46.261Z",
+ "finished_at": "2026-09-20T00:28:46.306Z",
+ "queued_at": "2026-09-20T00:28:45.867Z"
+ },
+ {
+ "model": "exo__llama-3-3-70b-instruct-8bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T00:28:46.346Z",
+ "finished_at": "2026-09-20T00:28:46.393Z",
+ "queued_at": "2026-09-20T00:28:45.908Z"
+ }
+ ]
+ },
+ {
+ "id": "929c2b71cba6",
+ "title": "Finance Competition #13 — 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": "2026-09-20T00:33:53.987Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "exo__glm-5-1-mxfp4-q8",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T00:33:54.176Z",
+ "finished_at": "2026-09-20T00:33:54.213Z",
+ "queued_at": "2026-09-20T00:33:54.018Z"
+ },
+ {
+ "model": "exo__qwen3-coder-480b-a35b-instruct-8bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T00:33:54.238Z",
+ "finished_at": "2026-09-20T00:33:54.275Z",
+ "queued_at": "2026-09-20T00:33:54.042Z"
+ },
+ {
+ "model": "exo__minimax-m2-5-6bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T00:33:54.305Z",
+ "finished_at": "2026-09-20T00:33:54.341Z",
+ "queued_at": "2026-09-20T00:33:54.069Z"
+ },
+ {
+ "model": "exo__minimax-m2-7-8bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T00:33:54.368Z",
+ "finished_at": "2026-09-20T00:33:54.406Z",
+ "queued_at": "2026-09-20T00:33:54.093Z"
+ },
+ {
+ "model": "exo__qwen3-5-122b-a10b-8bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T00:33:54.430Z",
+ "finished_at": "2026-09-20T00:33:54.469Z",
+ "queued_at": "2026-09-20T00:33:54.120Z"
+ },
+ {
+ "model": "exo__kimi-k2-instruct-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T00:33:54.498Z",
+ "finished_at": "2026-09-20T00:33:54.536Z",
+ "queued_at": "2026-09-20T00:33:54.147Z"
+ }
+ ]
+ },
+ {
+ "id": "8527b8ccaa71",
+ "title": "Design Competition #13 — 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": "2026-09-20T00:39:02.226Z",
+ "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": "2026-09-20T00:39:02.416Z",
+ "finished_at": "2026-09-20T00:39:02.455Z",
+ "queued_at": "2026-09-20T00:39:02.262Z"
+ },
+ {
+ "model": "exo__deepseek-v4-flash",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T00:39:02.474Z",
+ "finished_at": "2026-09-20T00:39:02.504Z",
+ "queued_at": "2026-09-20T00:39:02.294Z"
+ },
+ {
+ "model": "exo__qwen3-next-80b-a3b-thinking-8bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T00:39:02.527Z",
+ "finished_at": "2026-09-20T00:39:02.555Z",
+ "queued_at": "2026-09-20T00:39:02.326Z"
+ },
+ {
+ "model": "exo__deepseek-v4-pro",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T00:39:02.577Z",
+ "finished_at": "2026-09-20T00:39:02.616Z",
+ "queued_at": "2026-09-20T00:39:02.352Z"
+ },
+ {
+ "model": "exo__deepseek-v3-1-8bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T00:39:02.637Z",
+ "finished_at": "2026-09-20T00:39:02.664Z",
+ "queued_at": "2026-09-20T00:39:02.375Z"
+ },
+ {
+ "model": "exo__glm-5-8bit-mxfp8",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T00:39:02.683Z",
+ "finished_at": "2026-09-20T00:39:02.716Z",
+ "queued_at": "2026-09-20T00:39:02.395Z"
+ }
+ ]
+ },
+ {
+ "id": "281defee3d14",
+ "title": "Art Competition #27 — Playable Mondrian",
+ "prompt": "Build this as one complete, self-contained HTML file: A Mondrian composition you can play like an instrument: clicking each colored rectangle triggers a tone and a ripple, and a 'let it compose itself' mode slowly rearranges the grid to a generative rhythm. 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": "2026-09-20T00:44:10.646Z",
+ "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": "2026-09-20T00:44:10.937Z",
+ "finished_at": "2026-09-20T00:44:11.043Z",
+ "queued_at": "2026-09-20T00:44:10.692Z"
+ },
+ {
+ "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": "2026-09-20T00:44:11.098Z",
+ "finished_at": "2026-09-20T00:44:11.152Z",
+ "queued_at": "2026-09-20T00:44:10.734Z"
+ },
+ {
+ "model": "exo__kimi-k2-6",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T00:44:11.185Z",
+ "finished_at": "2026-09-20T00:44:11.220Z",
+ "queued_at": "2026-09-20T00:44:10.770Z"
+ },
+ {
+ "model": "exo__nvidia-nemotron-3-nano-30b-a3b-mlx-8bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T00:44:11.260Z",
+ "finished_at": "2026-09-20T00:44:11.311Z",
+ "queued_at": "2026-09-20T00:44:10.810Z"
+ },
+ {
+ "model": "exo__gemma-4-31b-it-8bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T00:44:11.357Z",
+ "finished_at": "2026-09-20T00:44:11.401Z",
+ "queued_at": "2026-09-20T00:44:10.851Z"
+ },
+ {
+ "model": "qwen3-14b",
+ "status": "done",
+ "error": null,
+ "seconds": 135,
+ "cost": 0,
+ "started_at": "2026-09-20T00:44:10.982Z",
+ "finished_at": "2026-09-20T00:46:25.897Z",
+ "queued_at": "2026-09-20T00:44:10.892Z",
+ "bytes": 9533,
+ "thumb": true,
+ "aiScore": null,
+ "aiReason": "judge failed: all vision panelists failed"
+ }
+ ],
+ "judging": false,
+ "aiPick": null,
+ "judged_at": "2026-09-20T00:46:27.994Z"
+ },
+ {
+ "id": "4ce263cc5a7b",
+ "title": "Culture Competition #26 — Festivals of Nowhere",
+ "prompt": "Build this as one complete, self-contained HTML file: A world map of INVENTED holidays where hovering a region launches its signature celebration in miniature (lanterns, confetti, fireworks) and a little passport stamps each one you visit. 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": "2026-09-20T00:51:27.132Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "mlx__qwen3-30b-a3b-instruct-2507-4bit",
+ "status": "running",
+ "error": null,
+ "seconds": null,
+ "cost": null,
+ "started_at": "2026-09-20T00:51:27.445Z",
+ "finished_at": null,
+ "queued_at": "2026-09-20T00:51:27.175Z"
+ },
+ {
+ "model": "exo__minimax-m2-7-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T00:51:27.521Z",
+ "finished_at": "2026-09-20T00:51:27.679Z",
+ "queued_at": "2026-09-20T00:51:27.227Z"
+ },
+ {
+ "model": "qwen25-7b",
+ "status": "error",
+ "error": "ollama bad response: 503",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T00:51:27.569Z",
+ "finished_at": "2026-09-20T00:51:27.807Z",
+ "queued_at": "2026-09-20T00:51:27.269Z"
+ },
+ {
+ "model": "mlx__qwen3-next-80b-a3b-instruct-4bit",
+ "status": "queued",
+ "error": null,
+ "seconds": null,
+ "cost": null,
+ "started_at": null,
+ "finished_at": null,
+ "queued_at": "2026-09-20T00:51:27.303Z"
+ },
+ {
+ "model": "exo__qwen3-coder-480b-a35b-instruct-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T00:51:27.745Z",
+ "finished_at": "2026-09-20T00:51:28.014Z",
+ "queued_at": "2026-09-20T00:51:27.349Z"
+ },
+ {
+ "model": "mac1__minicpm-v-latest",
+ "status": "error",
+ "error": "ollama bad response: 503",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T00:51:27.875Z",
+ "finished_at": "2026-09-20T00:51:28.134Z",
+ "queued_at": "2026-09-20T00:51:27.397Z"
+ }
+ ]
}
]
\ No newline at end of file
diff --git a/yolo/arena-loop-state.json b/yolo/arena-loop-state.json
index aa465db..4e63e2d 100644
--- a/yolo/arena-loop-state.json
+++ b/yolo/arena-loop-state.json
@@ -1 +1 @@
-{"promptIdx":3,"modelOffset":106,"compCount":{"Art":26,"Culture":25,"News":25,"Political Cartoon":25,"Games":13,"Real Work":13,"Data Viz":13,"Science":13,"Music":13,"Sports":13,"History":13,"Nature & Space":13,"Comedy":13,"Demoscene":12,"Finance":12,"Design":12},"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":7,"compCount":{"Art":27,"Culture":26,"News":25,"Political Cartoon":25,"Games":13,"Real Work":13,"Data Viz":13,"Science":13,"Music":13,"Sports":13,"History":13,"Nature & Space":13,"Comedy":13,"Demoscene":13,"Finance":13,"Design":13},"catIdx":18,"perCat":{"Art":2,"Culture":2,"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 179f9cf..08f2682 100644
--- a/yolo/daily-log.jsonl
+++ b/yolo/daily-log.jsonl
@@ -308,3 +308,7 @@
{"ts":"2026-09-20T00:13:28.945Z","id":"b4f06ded8ea7","promptId":"timeline-hist","category":"History","title":"History Competition #13 — Walk-Through Age of Invention","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
{"ts":"2026-09-20T00:18:37.298Z","id":"4dc5f4626e61","promptId":"starmap","category":"Nature & Space","title":"Nature & Space Competition #13 — Invent Your Own Constellations","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
{"ts":"2026-09-20T00:23:45.613Z","id":"ef38aa08c574","promptId":"meme","category":"Comedy","title":"Comedy Competition #13 — The Meme Generator That Fights Back","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-20T00:28:53.953Z","id":"bdffa2e51ea4","promptId":"plasma","category":"Demoscene","title":"Demoscene Competition #13 — Lava-Lamp Boot Screen","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-20T00:34:02.183Z","id":"929c2b71cba6","promptId":"portfolio","category":"Finance","title":"Finance Competition #13 — Galactic Exchange Portfolio","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-20T00:39:10.419Z","id":"8527b8ccaa71","promptId":"components","category":"Design","title":"Design Competition #13 — Design System Safari","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-20T00:46:27.026Z","id":"281defee3d14","promptId":"mondrian","category":"Art","title":"Art Competition #27 — Playable Mondrian","models":6,"done":1,"errored":5,"settled":true,"aiPick":null,"loop":true}
← 5fd3879 auto-data-snapshot: 2026-09-19T17:24:27 (3 data files) — dat
·
back to Model Arena
·
auto-data-snapshot: 2026-09-19T18:28:04 (3 data files) — dat b7ce66c →