← back to Model Arena
auto-data-snapshot: 2026-09-21T03:22:12 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl
b71d3e2ee708f63083ac230ff08908d98fa84676 · 2026-09-21 03:24:08 -0700 · auto-commit-fleet
Files touched
M data/challenges.jsonM yolo/arena-loop-state.jsonM yolo/daily-log.jsonl
Diff
commit b71d3e2ee708f63083ac230ff08908d98fa84676
Author: auto-commit-fleet <steve@designerwallcoverings.com>
Date: Mon Sep 21 03:24:08 2026 -0700
auto-data-snapshot: 2026-09-21T03:22:12 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl
---
data/challenges.json | 299 ++++++++++++++++++++++++++++++++++++++++++++-
yolo/arena-loop-state.json | 2 +-
yolo/daily-log.jsonl | 5 +
3 files changed, 300 insertions(+), 6 deletions(-)
diff --git a/data/challenges.json b/data/challenges.json
index 1e5a76d..19aada4 100644
--- a/data/challenges.json
+++ b/data/challenges.json
@@ -79180,16 +79180,18 @@
"finished_at": "2026-09-21T09:45:20.969Z",
"queued_at": "2026-09-21T09:43:17.972Z",
"bytes": 7463,
- "thumb": true
+ "thumb": true,
+ "aiScore": null,
+ "aiReason": "judge failed: all vision panelists failed"
},
{
"model": "mlx__qwen3-30b-a3b-instruct-2507-4bit",
- "status": "running",
- "error": null,
- "seconds": null,
+ "status": "error",
+ "error": "timeout after 600s",
+ "seconds": 600,
"cost": null,
"started_at": "2026-09-21T09:43:18.153Z",
- "finished_at": null,
+ "finished_at": "2026-09-21T09:53:18.182Z",
"queued_at": "2026-09-21T09:43:18.005Z"
},
{
@@ -79212,6 +79214,293 @@
"finished_at": "2026-09-21T09:45:21.198Z",
"queued_at": "2026-09-21T09:43:18.063Z"
}
+ ],
+ "judging": false,
+ "aiPick": null,
+ "judged_at": "2026-09-21T09:53:18.394Z"
+ },
+ {
+ "id": "5f123acf0a99",
+ "title": "Art Competition #60 — Swarm Typography Poster",
+ "prompt": "Build this as one complete, self-contained HTML file: A kinetic-type poster for an INVENTED avant-garde festival where the headline letters behave like a flocking swarm — scattering from the cursor and re-forming the title — with a slider that morphs the mood from 'whisper' to 'scream'. 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": "2026-09-21T09:58:18.464Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "mlx__qwen3-next-80b-a3b-instruct-4bit",
+ "status": "error",
+ "error": "timeout after 600s",
+ "seconds": 600,
+ "cost": null,
+ "started_at": "2026-09-21T09:58:18.856Z",
+ "finished_at": "2026-09-21T10:08:18.984Z",
+ "queued_at": "2026-09-21T09:58:18.516Z"
+ },
+ {
+ "model": "exo__qwen3-coder-480b-a35b-instruct-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T09:58:18.898Z",
+ "finished_at": "2026-09-21T09:58:18.993Z",
+ "queued_at": "2026-09-21T09:58:18.602Z"
+ },
+ {
+ "model": "mac1__minicpm-v-latest",
+ "status": "error",
+ "error": "ollama bad response: 503",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T09:58:18.947Z",
+ "finished_at": "2026-09-21T09:58:19.220Z",
+ "queued_at": "2026-09-21T09:58:18.675Z"
+ },
+ {
+ "model": "exo__qwen3-5-122b-a10b-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T09:58:19.053Z",
+ "finished_at": "2026-09-21T09:58:19.108Z",
+ "queued_at": "2026-09-21T09:58:18.727Z"
+ },
+ {
+ "model": "mac1__qwen2-5vl-7b",
+ "status": "error",
+ "error": "ollama bad response: 503",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T09:58:19.271Z",
+ "finished_at": "2026-09-21T09:58:19.503Z",
+ "queued_at": "2026-09-21T09:58:18.773Z"
+ },
+ {
+ "model": "exo__gemma-4-26b-a4b-it-6bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T09:58:19.162Z",
+ "finished_at": "2026-09-21T09:58:19.329Z",
+ "queued_at": "2026-09-21T09:58:18.808Z"
+ }
+ ]
+ },
+ {
+ "id": "0fcaad5023d2",
+ "title": "Culture Competition #59 — The Last Speaker",
+ "prompt": "Build this as one complete, self-contained HTML file: An interactive 'sound of a dying language' explainer for an INVENTED tongue: click words on a fading map to hear invented phonemes, watch the speaker-count clock tick down, and 'save' words into a phrasebook. 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": "2026-09-21T10:13:19.180Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "exo__qwen3-6-35b-a3b-bf16",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T10:13:19.395Z",
+ "finished_at": "2026-09-21T10:13:19.423Z",
+ "queued_at": "2026-09-21T10:13:19.214Z"
+ },
+ {
+ "model": "exo__qwen3-vl-4b-instruct-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T10:13:19.449Z",
+ "finished_at": "2026-09-21T10:13:19.478Z",
+ "queued_at": "2026-09-21T10:13:19.246Z"
+ },
+ {
+ "model": "exo__minimax-m2-7",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T10:13:19.505Z",
+ "finished_at": "2026-09-21T10:13:19.536Z",
+ "queued_at": "2026-09-21T10:13:19.276Z"
+ },
+ {
+ "model": "exo__llama-3-3-70b-instruct-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T10:13:19.561Z",
+ "finished_at": "2026-09-21T10:13:19.597Z",
+ "queued_at": "2026-09-21T10:13:19.301Z"
+ },
+ {
+ "model": "exo__gemma-4-e2b-it-bf16",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T10:13:19.622Z",
+ "finished_at": "2026-09-21T10:13:19.651Z",
+ "queued_at": "2026-09-21T10:13:19.331Z"
+ },
+ {
+ "model": "exo__qwen3-next-80b-a3b-instruct-8bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T10:13:19.675Z",
+ "finished_at": "2026-09-21T10:13:19.703Z",
+ "queued_at": "2026-09-21T10:13:19.367Z"
+ }
+ ]
+ },
+ {
+ "id": "7fdef3ef7c1f",
+ "title": "News Competition #59 — Absurd 24-Hour News",
+ "prompt": "Build this as one complete, self-contained HTML file: A satirical INVENTED 24-hour news channel landing where three breaking stories escalate absurdly in real time via a live ticker, a 'BREAKING' klaxon toggle, and a category filter that changes the channel's whole color mood. 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": "2026-09-21T10:18:27.429Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "exo__qwen3-6-27b-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T10:18:27.676Z",
+ "finished_at": "2026-09-21T10:18:27.721Z",
+ "queued_at": "2026-09-21T10:18:27.464Z"
+ },
+ {
+ "model": "exo__glm-4-7-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T10:18:27.750Z",
+ "finished_at": "2026-09-21T10:18:27.782Z",
+ "queued_at": "2026-09-21T10:18:27.491Z"
+ },
+ {
+ "model": "exo__gemma-4-31b-it-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T10:18:27.810Z",
+ "finished_at": "2026-09-21T10:18:27.839Z",
+ "queued_at": "2026-09-21T10:18:27.549Z"
+ },
+ {
+ "model": "exo__nvidia-nemotron-3-nano-30b-a3b-mlx-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T10:18:27.864Z",
+ "finished_at": "2026-09-21T10:18:27.895Z",
+ "queued_at": "2026-09-21T10:18:27.596Z"
+ },
+ {
+ "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": "2026-09-21T10:18:27.923Z",
+ "finished_at": "2026-09-21T10:18:27.953Z",
+ "queued_at": "2026-09-21T10:18:27.620Z"
+ },
+ {
+ "model": "exo__qwen3-coder-next-6bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T10:18:27.980Z",
+ "finished_at": "2026-09-21T10:18:28.016Z",
+ "queued_at": "2026-09-21T10:18:27.646Z"
+ }
+ ]
+ },
+ {
+ "id": "0c6e90edc897",
+ "title": "Political Cartoon Competition #59 — Ship of State by Committee",
+ "prompt": "Build this as one complete, self-contained HTML file: A single bold SVG metaphor illustration for an INVENTED political theme — 'the ship of state steered by committee' — where dragging elements changes the metaphor's meaning and the caption adapts. Light/dark toggle. 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": "Political Cartoon",
+ "designTools": false,
+ "created_at": "2026-09-21T10:23:35.713Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "exo__step-3-5-flash-6bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T10:23:35.981Z",
+ "finished_at": "2026-09-21T10:23:36.023Z",
+ "queued_at": "2026-09-21T10:23:35.757Z"
+ },
+ {
+ "model": "exo__qwen3-next-80b-a3b-thinking-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T10:23:36.051Z",
+ "finished_at": "2026-09-21T10:23:36.092Z",
+ "queued_at": "2026-09-21T10:23:35.802Z"
+ },
+ {
+ "model": "exo__deepseek-v3-1-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T10:23:36.121Z",
+ "finished_at": "2026-09-21T10:23:36.162Z",
+ "queued_at": "2026-09-21T10:23:35.877Z"
+ },
+ {
+ "model": "exo__llama-3-1-nemotron-70b-instruct-hf-8bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T10:23:36.197Z",
+ "finished_at": "2026-09-21T10:23:36.232Z",
+ "queued_at": "2026-09-21T10:23:35.910Z"
+ },
+ {
+ "model": "exo__gemma-4-e4b-it-6bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T10:23:36.260Z",
+ "finished_at": "2026-09-21T10:23:36.289Z",
+ "queued_at": "2026-09-21T10:23:35.934Z"
+ },
+ {
+ "model": "exo__nvidia-nemotron-3-nano-30b-a3b-mlx-5bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T10:23:36.314Z",
+ "finished_at": "2026-09-21T10:23:36.345Z",
+ "queued_at": "2026-09-21T10:23:35.957Z"
+ }
]
}
]
\ No newline at end of file
diff --git a/yolo/arena-loop-state.json b/yolo/arena-loop-state.json
index dd680f1..c1a4c2c 100644
--- a/yolo/arena-loop-state.json
+++ b/yolo/arena-loop-state.json
@@ -1 +1 @@
-{"promptIdx":3,"modelOffset":4,"compCount":{"Art":59,"Culture":58,"News":58,"Political Cartoon":58,"Games":29,"Real Work":29,"Data Viz":29,"Science":29,"Music":29,"Sports":29,"History":29,"Nature & Space":29,"Comedy":29,"Demoscene":29,"Finance":29,"Design":29},"catIdx":0,"perCat":{"Art":2,"Culture":2,"News":2,"Political Cartoon":2,"Games":2,"Real Work":2,"Data Viz":2,"Science":2,"Music":2,"Sports":2,"History":2,"Nature & Space":2,"Comedy":2,"Demoscene":2,"Finance":2,"Design":2}}
\ No newline at end of file
+{"promptIdx":3,"modelOffset":28,"compCount":{"Art":60,"Culture":59,"News":59,"Political Cartoon":59,"Games":29,"Real Work":29,"Data Viz":29,"Science":29,"Music":29,"Sports":29,"History":29,"Nature & Space":29,"Comedy":29,"Demoscene":29,"Finance":29,"Design":29},"catIdx":4,"perCat":{"Art":3,"Culture":3,"News":3,"Political Cartoon":3,"Games":2,"Real Work":2,"Data Viz":2,"Science":2,"Music":2,"Sports":2,"History":2,"Nature & Space":2,"Comedy":2,"Demoscene":2,"Finance":2,"Design":2}}
\ No newline at end of file
diff --git a/yolo/daily-log.jsonl b/yolo/daily-log.jsonl
index d48efb9..a429cfb 100644
--- a/yolo/daily-log.jsonl
+++ b/yolo/daily-log.jsonl
@@ -635,3 +635,8 @@
{"ts":"2026-09-21T09:28:01.160Z","id":"01d229eecf9e","promptId":"mondrian","category":"Art","title":"Art Competition #59 — Playable Mondrian","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
{"ts":"2026-09-21T09:33:09.437Z","id":"cb2896bae75d","promptId":"culture-map","category":"Culture","title":"Culture Competition #58 — Festivals of Nowhere","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
{"ts":"2026-09-21T09:38:17.864Z","id":"be3ec3fcc61b","promptId":"econ-brief","category":"News","title":"News Competition #58 — Teletext Econ Briefing","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-21T09:53:18.428Z","id":"e5f0df50ebb9","promptId":"satire-strip","category":"Political Cartoon","title":"Political Cartoon Competition #58 — The Form to Request a Form","models":6,"done":1,"errored":5,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-21T10:08:19.156Z","id":"5f123acf0a99","promptId":"kinetic-type","category":"Art","title":"Art Competition #60 — Swarm Typography Poster","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-21T10:13:27.401Z","id":"0fcaad5023d2","promptId":"languages","category":"Culture","title":"Culture Competition #59 — The Last Speaker","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-21T10:18:35.681Z","id":"7fdef3ef7c1f","promptId":"news-ticker","category":"News","title":"News Competition #59 — Absurd 24-Hour News","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-21T10:23:43.986Z","id":"0c6e90edc897","promptId":"metaphor","category":"Political Cartoon","title":"Political Cartoon Competition #59 — Ship of State by Committee","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
← 6a949b4 auto-data-snapshot: 2026-09-21T02:49:08 (3 data files) — dat
·
back to Model Arena
·
auto-data-snapshot: 2026-09-21T03:55:17 (3 data files) — dat dd98530 →