← back to Model Arena
auto-data-snapshot: 2026-09-20T01:05:15 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl
151d95c66cb23d23194a4b923df4296fae274217 · 2026-09-20 01:07:06 -0700 · auto-commit-fleet
Files touched
M data/challenges.jsonM yolo/arena-loop-state.jsonM yolo/daily-log.jsonl
Diff
commit 151d95c66cb23d23194a4b923df4296fae274217
Author: auto-commit-fleet <steve@designerwallcoverings.com>
Date: Sun Sep 20 01:07:06 2026 -0700
auto-data-snapshot: 2026-09-20T01:05:15 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl
---
data/challenges.json | 284 +++++++++++++++++++++++++++++++++++++++++++++
yolo/arena-loop-state.json | 2 +-
yolo/daily-log.jsonl | 4 +
3 files changed, 289 insertions(+), 1 deletion(-)
diff --git a/data/challenges.json b/data/challenges.json
index 55dda92..14605c8 100644
--- a/data/challenges.json
+++ b/data/challenges.json
@@ -60778,5 +60778,289 @@
"judging": false,
"aiPick": null,
"judged_at": "2026-09-20T07:31:47.448Z"
+ },
+ {
+ "id": "974dcb4c40fa",
+ "title": "News Competition #33 — Election Night: Floating Isles",
+ "prompt": "Build this as one complete, self-contained HTML file: An election-night 'war room' for an INVENTED nation of floating islands: a live map colors in as returns land, a needle swings, invented pundits drop one-liners, and a 'what if' slider re-runs the result. 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": "2026-09-20T07:36:47.532Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "mlx__qwen3-next-80b-a3b-instruct-4bit",
+ "status": "error",
+ "error": "timeout after 600s",
+ "seconds": 600,
+ "cost": null,
+ "started_at": "2026-09-20T07:36:47.837Z",
+ "finished_at": "2026-09-20T07:46:47.995Z",
+ "queued_at": "2026-09-20T07:36:47.588Z"
+ },
+ {
+ "model": "exo__qwen3-coder-480b-a35b-instruct-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T07:36:47.885Z",
+ "finished_at": "2026-09-20T07:36:47.996Z",
+ "queued_at": "2026-09-20T07:36:47.627Z"
+ },
+ {
+ "model": "mac1__minicpm-v-latest",
+ "status": "error",
+ "error": "ollama bad response: 503",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T07:36:47.931Z",
+ "finished_at": "2026-09-20T07:36:48.239Z",
+ "queued_at": "2026-09-20T07:36:47.654Z"
+ },
+ {
+ "model": "exo__qwen3-5-122b-a10b-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T07:36:48.041Z",
+ "finished_at": "2026-09-20T07:36:48.092Z",
+ "queued_at": "2026-09-20T07:36:47.723Z"
+ },
+ {
+ "model": "mac1__qwen2-5vl-7b",
+ "status": "error",
+ "error": "ollama bad response: 503",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T07:36:48.275Z",
+ "finished_at": "2026-09-20T07:36:48.501Z",
+ "queued_at": "2026-09-20T07:36:47.754Z"
+ },
+ {
+ "model": "exo__gemma-4-26b-a4b-it-6bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T07:36:48.134Z",
+ "finished_at": "2026-09-20T07:36:48.186Z",
+ "queued_at": "2026-09-20T07:36:47.783Z"
+ }
+ ]
+ },
+ {
+ "id": "11a85b98c113",
+ "title": "Political Cartoon Competition #33 — The Seesaw Debate",
+ "prompt": "Build this as one complete, self-contained HTML file: An original SVG editorial cartoon about an INVENTED debate ('should robots get weekends?'): a seesaw of absurd figures the viewer can tip, with a caption that rewrites itself for each side. Non-partisan, invented symbols only. 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": "2026-09-20T07:51:48.161Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "exo__qwen3-6-35b-a3b-bf16",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T07:51:48.495Z",
+ "finished_at": "2026-09-20T07:51:48.554Z",
+ "queued_at": "2026-09-20T07:51:48.204Z"
+ },
+ {
+ "model": "exo__qwen3-vl-4b-instruct-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T07:51:48.601Z",
+ "finished_at": "2026-09-20T07:51:48.660Z",
+ "queued_at": "2026-09-20T07:51:48.249Z"
+ },
+ {
+ "model": "exo__minimax-m2-7",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T07:51:48.711Z",
+ "finished_at": "2026-09-20T07:51:48.754Z",
+ "queued_at": "2026-09-20T07:51:48.304Z"
+ },
+ {
+ "model": "exo__llama-3-3-70b-instruct-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T07:51:48.785Z",
+ "finished_at": "2026-09-20T07:51:48.829Z",
+ "queued_at": "2026-09-20T07:51:48.353Z"
+ },
+ {
+ "model": "exo__gemma-4-e2b-it-bf16",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T07:51:48.872Z",
+ "finished_at": "2026-09-20T07:51:48.902Z",
+ "queued_at": "2026-09-20T07:51:48.408Z"
+ },
+ {
+ "model": "exo__qwen3-next-80b-a3b-instruct-8bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T07:51:48.933Z",
+ "finished_at": "2026-09-20T07:51:48.976Z",
+ "queued_at": "2026-09-20T07:51:48.455Z"
+ }
+ ]
+ },
+ {
+ "id": "1d7789f1b862",
+ "title": "Games Competition #17 — Wake the Dragon Breakout",
+ "prompt": "Build this as one complete, self-contained HTML file: Brick-breaker where the bricks are a sleeping dragon's scales — knock them loose and the dragon slowly wakes (eyes open, breathing quickens). The paddle is a shield; a caught power-up briefly lets you paint new bricks. 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": "Games",
+ "designTools": false,
+ "created_at": "2026-09-20T07:56:56.540Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "exo__qwen3-6-27b-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T07:56:56.751Z",
+ "finished_at": "2026-09-20T07:56:56.775Z",
+ "queued_at": "2026-09-20T07:56:56.571Z"
+ },
+ {
+ "model": "exo__glm-4-7-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T07:56:56.795Z",
+ "finished_at": "2026-09-20T07:56:56.819Z",
+ "queued_at": "2026-09-20T07:56:56.604Z"
+ },
+ {
+ "model": "exo__gemma-4-31b-it-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T07:56:56.844Z",
+ "finished_at": "2026-09-20T07:56:56.869Z",
+ "queued_at": "2026-09-20T07:56:56.633Z"
+ },
+ {
+ "model": "exo__nvidia-nemotron-3-nano-30b-a3b-mlx-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T07:56:56.888Z",
+ "finished_at": "2026-09-20T07:56:56.911Z",
+ "queued_at": "2026-09-20T07:56:56.669Z"
+ },
+ {
+ "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": "2026-09-20T07:56:56.930Z",
+ "finished_at": "2026-09-20T07:56:56.951Z",
+ "queued_at": "2026-09-20T07:56:56.702Z"
+ },
+ {
+ "model": "exo__qwen3-coder-next-6bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T07:56:56.969Z",
+ "finished_at": "2026-09-20T07:56:56.991Z",
+ "queued_at": "2026-09-20T07:56:56.725Z"
+ }
+ ]
+ },
+ {
+ "id": "4e712ca92fad",
+ "title": "Real Work Competition #17 — Timesheet Garden",
+ "prompt": "Build this as one complete, self-contained HTML file: A timesheet that grows your week as a garden — each logged hour sprouts a plant in the right plot, overtime wilts, and an 'invoice' view harvests it into a clean printable total with rate math and validation. 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": "2026-09-20T08:02:04.821Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "exo__step-3-5-flash-6bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T08:02:05.054Z",
+ "finished_at": "2026-09-20T08:02:05.091Z",
+ "queued_at": "2026-09-20T08:02:04.850Z"
+ },
+ {
+ "model": "exo__qwen3-next-80b-a3b-thinking-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T08:02:05.120Z",
+ "finished_at": "2026-09-20T08:02:05.149Z",
+ "queued_at": "2026-09-20T08:02:04.885Z"
+ },
+ {
+ "model": "exo__deepseek-v3-1-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T08:02:05.168Z",
+ "finished_at": "2026-09-20T08:02:05.190Z",
+ "queued_at": "2026-09-20T08:02:04.921Z"
+ },
+ {
+ "model": "exo__llama-3-1-nemotron-70b-instruct-hf-8bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T08:02:05.211Z",
+ "finished_at": "2026-09-20T08:02:05.243Z",
+ "queued_at": "2026-09-20T08:02:04.957Z"
+ },
+ {
+ "model": "exo__gemma-4-e4b-it-6bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T08:02:05.268Z",
+ "finished_at": "2026-09-20T08:02:05.298Z",
+ "queued_at": "2026-09-20T08:02:04.994Z"
+ },
+ {
+ "model": "exo__nvidia-nemotron-3-nano-30b-a3b-mlx-5bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T08:02:05.324Z",
+ "finished_at": "2026-09-20T08:02:05.462Z",
+ "queued_at": "2026-09-20T08:02:05.022Z"
+ }
+ ]
}
]
\ No newline at end of file
diff --git a/yolo/arena-loop-state.json b/yolo/arena-loop-state.json
index e98d65b..a996544 100644
--- a/yolo/arena-loop-state.json
+++ b/yolo/arena-loop-state.json
@@ -1 +1 @@
-{"promptIdx":3,"modelOffset":4,"compCount":{"Art":34,"Culture":33,"News":32,"Political Cartoon":32,"Games":16,"Real Work":16,"Data Viz":16,"Science":16,"Music":16,"Sports":16,"History":16,"Nature & Space":16,"Comedy":16,"Demoscene":16,"Finance":16,"Design":16},"catIdx":2,"perCat":{"Art":1,"Culture":1,"News":4,"Political Cartoon":4,"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
+{"promptIdx":3,"modelOffset":28,"compCount":{"Art":34,"Culture":33,"News":33,"Political Cartoon":33,"Games":17,"Real Work":17,"Data Viz":16,"Science":16,"Music":16,"Sports":16,"History":16,"Nature & Space":16,"Comedy":16,"Demoscene":16,"Finance":16,"Design":16},"catIdx":6,"perCat":{"Art":1,"Culture":1,"News":1,"Political Cartoon":1,"Games":2,"Real Work":2,"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 149c9c3..2efe46e 100644
--- a/yolo/daily-log.jsonl
+++ b/yolo/daily-log.jsonl
@@ -377,3 +377,7 @@
{"ts":"2026-09-20T07:11:38.534Z","id":"8b709295398b","promptId":"civic-explainer","category":"Political Cartoon","title":"Political Cartoon Competition #32 — How a Law Gets Passed (Rube Goldberg)","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
{"ts":"2026-09-20T07:16:46.863Z","id":"84933e8bce33","promptId":"gen-art","category":"Art","title":"Art Competition #34 — Living Ink Canvas","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
{"ts":"2026-09-20T07:31:47.485Z","id":"4c82ed15d8dd","promptId":"museum","category":"Culture","title":"Culture Competition #33 — Museum of a Lost Civilization","models":6,"done":1,"errored":5,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-20T07:46:48.120Z","id":"974dcb4c40fa","promptId":"election-viz","category":"News","title":"News Competition #33 — Election Night: Floating Isles","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-20T07:51:56.496Z","id":"11a85b98c113","promptId":"editorial-cartoon","category":"Political Cartoon","title":"Political Cartoon Competition #33 — The Seesaw Debate","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-20T07:57:04.754Z","id":"1d7789f1b862","promptId":"breakout","category":"Games","title":"Games Competition #17 — Wake the Dragon Breakout","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-20T08:02:13.065Z","id":"4e712ca92fad","promptId":"timesheet","category":"Real Work","title":"Real Work Competition #17 — Timesheet Garden","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
← 85154f3 auto-data-snapshot: 2026-09-20T00:31:26 (3 data files) — dat
·
back to Model Arena
·
auto-data-snapshot: 2026-09-20T01:38:41 (3 data files) — dat 04e8d5c →