← back to Model Arena
auto-data-snapshot: 2026-09-21T05:33:35 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl
fe9d66459edb232a376d93a160ba109523c7122e · 2026-09-21 05:34:36 -0700 · auto-commit-fleet
Files touched
M data/challenges.jsonM yolo/arena-loop-state.jsonM yolo/daily-log.jsonl
Diff
commit fe9d66459edb232a376d93a160ba109523c7122e
Author: auto-commit-fleet <steve@designerwallcoverings.com>
Date: Mon Sep 21 05:34:36 2026 -0700
auto-data-snapshot: 2026-09-21T05:33:35 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl
---
data/challenges.json | 225 +++++++++++++++++++++++++++++++++++++++++++--
yolo/arena-loop-state.json | 2 +-
yolo/daily-log.jsonl | 3 +
3 files changed, 220 insertions(+), 10 deletions(-)
diff --git a/data/challenges.json b/data/challenges.json
index 6f0de84..cd0b93d 100644
--- a/data/challenges.json
+++ b/data/challenges.json
@@ -80728,12 +80728,12 @@
"runs": [
{
"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": "2026-09-21T11:59:18.715Z",
- "finished_at": null,
+ "finished_at": "2026-09-21T12:09:18.858Z",
"queued_at": "2026-09-21T11:59:18.441Z"
},
{
@@ -80758,12 +80758,12 @@
},
{
"model": "mlx__qwen3-next-80b-a3b-instruct-4bit",
- "status": "queued",
- "error": null,
- "seconds": null,
+ "status": "error",
+ "error": "timeout after 600s",
+ "seconds": 600,
"cost": null,
- "started_at": null,
- "finished_at": null,
+ "started_at": "2026-09-21T12:09:18.943Z",
+ "finished_at": "2026-09-21T12:19:19.024Z",
"queued_at": "2026-09-21T11:59:18.572Z"
},
{
@@ -80787,5 +80787,212 @@
"queued_at": "2026-09-21T11:59:18.681Z"
}
]
+ },
+ {
+ "id": "403386822437",
+ "title": "News Competition #61 — 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": "2026-09-21T12:24:19.441Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "exo__qwen3-5-122b-a10b-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T12:24:19.737Z",
+ "finished_at": "2026-09-21T12:24:19.810Z",
+ "queued_at": "2026-09-21T12:24:19.488Z"
+ },
+ {
+ "model": "mac1__qwen2-5vl-7b",
+ "status": "error",
+ "error": "ollama bad response: 503",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T12:24:19.764Z",
+ "finished_at": "2026-09-21T12:24:19.997Z",
+ "queued_at": "2026-09-21T12:24:19.531Z"
+ },
+ {
+ "model": "exo__gemma-4-26b-a4b-it-6bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T12:24:19.856Z",
+ "finished_at": "2026-09-21T12:24:19.913Z",
+ "queued_at": "2026-09-21T12:24:19.575Z"
+ },
+ {
+ "model": "exo__qwen3-6-35b-a3b-bf16",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T12:24:19.954Z",
+ "finished_at": "2026-09-21T12:24:20.035Z",
+ "queued_at": "2026-09-21T12:24:19.613Z"
+ },
+ {
+ "model": "exo__qwen3-vl-4b-instruct-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T12:24:20.069Z",
+ "finished_at": "2026-09-21T12:24:20.101Z",
+ "queued_at": "2026-09-21T12:24:19.665Z"
+ },
+ {
+ "model": "exo__minimax-m2-7",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T12:24:20.149Z",
+ "finished_at": "2026-09-21T12:24:20.194Z",
+ "queued_at": "2026-09-21T12:24:19.707Z"
+ }
+ ]
+ },
+ {
+ "id": "f588cbb2f195",
+ "title": "Political Cartoon Competition #61 — 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": "2026-09-21T12:29:27.808Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "exo__llama-3-3-70b-instruct-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T12:29:28.374Z",
+ "finished_at": "2026-09-21T12:29:28.527Z",
+ "queued_at": "2026-09-21T12:29:27.894Z"
+ },
+ {
+ "model": "exo__gemma-4-e2b-it-bf16",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T12:29:28.611Z",
+ "finished_at": "2026-09-21T12:29:28.695Z",
+ "queued_at": "2026-09-21T12:29:27.973Z"
+ },
+ {
+ "model": "exo__qwen3-next-80b-a3b-instruct-8bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T12:29:28.792Z",
+ "finished_at": "2026-09-21T12:29:28.846Z",
+ "queued_at": "2026-09-21T12:29:28.057Z"
+ },
+ {
+ "model": "exo__qwen3-6-27b-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T12:29:28.926Z",
+ "finished_at": "2026-09-21T12:29:28.985Z",
+ "queued_at": "2026-09-21T12:29:28.153Z"
+ },
+ {
+ "model": "exo__glm-4-7-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T12:29:29.064Z",
+ "finished_at": "2026-09-21T12:29:29.133Z",
+ "queued_at": "2026-09-21T12:29:28.219Z"
+ },
+ {
+ "model": "exo__gemma-4-31b-it-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-21T12:29:29.195Z",
+ "finished_at": "2026-09-21T12:29:29.258Z",
+ "queued_at": "2026-09-21T12:29:28.297Z"
+ }
+ ]
+ },
+ {
+ "id": "b263dec70448",
+ "title": "Games Competition #31 — Comet Snake in a Dying Galaxy",
+ "prompt": "Build this as one complete, self-contained HTML file: Snake, but the snake is a comet and the arena is a shrinking galaxy: eating stars grows your tail AND bends gravity, near-misses trigger slow-mo, and the high score is logged as a named 'constellation'. 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": "2026-09-21T12:34:36.430Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "exo__nvidia-nemotron-3-nano-30b-a3b-mlx-4bit",
+ "status": "queued",
+ "error": null,
+ "seconds": null,
+ "cost": null,
+ "started_at": null,
+ "finished_at": null,
+ "queued_at": "2026-09-21T12:34:36.484Z"
+ },
+ {
+ "model": "exo__llama-3-1-nemotron-nano-4b-v1-1-4bit",
+ "status": "queued",
+ "error": null,
+ "seconds": null,
+ "cost": null,
+ "started_at": null,
+ "finished_at": null,
+ "queued_at": "2026-09-21T12:34:36.554Z"
+ },
+ {
+ "model": "exo__qwen3-coder-next-6bit",
+ "status": "queued",
+ "error": null,
+ "seconds": null,
+ "cost": null,
+ "started_at": null,
+ "finished_at": null,
+ "queued_at": "2026-09-21T12:34:36.585Z"
+ },
+ {
+ "model": "exo__step-3-5-flash-6bit",
+ "status": "queued",
+ "error": null,
+ "seconds": null,
+ "cost": null,
+ "started_at": null,
+ "finished_at": null,
+ "queued_at": "2026-09-21T12:34:36.611Z"
+ },
+ {
+ "model": "exo__qwen3-next-80b-a3b-thinking-4bit",
+ "status": "queued",
+ "error": null,
+ "seconds": null,
+ "cost": null
+ },
+ {
+ "model": "exo__deepseek-v3-1-4bit",
+ "status": "queued",
+ "error": null,
+ "seconds": null,
+ "cost": null
+ }
+ ]
}
]
\ No newline at end of file
diff --git a/yolo/arena-loop-state.json b/yolo/arena-loop-state.json
index c2829a6..2f799ab 100644
--- a/yolo/arena-loop-state.json
+++ b/yolo/arena-loop-state.json
@@ -1 +1 @@
-{"promptIdx":3,"modelOffset":7,"compCount":{"Art":62,"Culture":61,"News":60,"Political Cartoon":60,"Games":30,"Real Work":30,"Data Viz":30,"Science":30,"Music":30,"Sports":30,"History":30,"Nature & Space":30,"Comedy":30,"Demoscene":30,"Finance":30,"Design":30},"catIdx":2,"perCat":{"Art":1,"Culture":1,"News":4,"Political Cartoon":4,"Games":3,"Real Work":3,"Data Viz":3,"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":19,"compCount":{"Art":62,"Culture":61,"News":61,"Political Cartoon":61,"Games":30,"Real Work":30,"Data Viz":30,"Science":30,"Music":30,"Sports":30,"History":30,"Nature & Space":30,"Comedy":30,"Demoscene":30,"Finance":30,"Design":30},"catIdx":4,"perCat":{"Art":1,"Culture":1,"News":1,"Political Cartoon":1,"Games":3,"Real Work":3,"Data Viz":3,"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
diff --git a/yolo/daily-log.jsonl b/yolo/daily-log.jsonl
index fe10f47..88e8f35 100644
--- a/yolo/daily-log.jsonl
+++ b/yolo/daily-log.jsonl
@@ -657,3 +657,6 @@
{"ts":"2026-09-21T11:40:49.157Z","id":"5459a6d42743","promptId":"climate-story","category":"News","title":"News Competition #60 — The City That Floods As You Scroll","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
{"ts":"2026-09-21T11:45:57.848Z","id":"6fac67a5ab78","promptId":"civic-explainer","category":"Political Cartoon","title":"Political Cartoon Competition #60 — How a Law Gets Passed (Rube Goldberg)","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
{"ts":"2026-09-21T11:54:18.317Z","id":"3affa90a789a","promptId":"gen-art","category":"Art","title":"Art Competition #62 — Living Ink Canvas","models":6,"done":1,"errored":5,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-21T12:19:19.408Z","id":"9ce6dd2bd4e4","promptId":"museum","category":"Culture","title":"Culture Competition #61 — Museum of a Lost Civilization","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-21T12:24:27.742Z","id":"403386822437","promptId":"election-viz","category":"News","title":"News Competition #61 — Election Night: Floating Isles","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-21T12:29:36.385Z","id":"f588cbb2f195","promptId":"editorial-cartoon","category":"Political Cartoon","title":"Political Cartoon Competition #61 — The Seesaw Debate","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
← bf91f92 auto-data-snapshot: 2026-09-21T05:01:17 (3 data files) — dat
·
back to Model Arena
·
auto-data-snapshot: 2026-09-21T06:06:14 (3 data files) — dat 08a9764 →