← back to Model Arena
auto-data-snapshot: 2026-09-26T10:42:21 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl
96fe2ef144518c9d5c77506264623cfa90c0d2ac · 2026-09-26 10:43:01 -0700 · auto-commit-fleet
Files touched
M data/challenges.jsonM yolo/arena-loop-state.jsonM yolo/daily-log.jsonl
Diff
commit 96fe2ef144518c9d5c77506264623cfa90c0d2ac
Author: auto-commit-fleet <steve@designerwallcoverings.com>
Date: Sat Sep 26 10:43:01 2026 -0700
auto-data-snapshot: 2026-09-26T10:42:21 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl
---
data/challenges.json | 163 +++++++++++++++++++++++++++++++++++++++++++--
yolo/arena-loop-state.json | 2 +-
yolo/daily-log.jsonl | 1 +
3 files changed, 160 insertions(+), 6 deletions(-)
diff --git a/data/challenges.json b/data/challenges.json
index 39a3296..049b2d9 100644
--- a/data/challenges.json
+++ b/data/challenges.json
@@ -94266,7 +94266,7 @@
"finished_at": null,
"queued_at": "2026-09-26T15:45:49.869Z",
"fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3-30B-A3B-Instruct-2507-4bit)",
- "resumes": 2
+ "resumes": 3
},
{
"model": "exo__gemma-4-e2b-it-bf16",
@@ -94277,7 +94277,7 @@
"started_at": null,
"finished_at": null,
"queued_at": "2026-09-26T15:45:49.924Z",
- "resumes": 2
+ "resumes": 3
},
{
"model": "exo__qwen3-next-80b-a3b-instruct-8bit",
@@ -94288,7 +94288,7 @@
"started_at": null,
"finished_at": null,
"queued_at": "2026-09-26T15:45:50.215Z",
- "resumes": 2
+ "resumes": 3
},
{
"model": "exo__qwen3-6-27b-4bit",
@@ -94299,7 +94299,7 @@
"started_at": null,
"finished_at": null,
"queued_at": "2026-09-26T15:45:50.352Z",
- "resumes": 2
+ "resumes": 3
},
{
"model": "exo__glm-4-7-4bit",
@@ -94310,7 +94310,7 @@
"started_at": null,
"finished_at": null,
"queued_at": "2026-09-26T15:45:50.626Z",
- "resumes": 2
+ "resumes": 3
}
],
"aiPick": null
@@ -94468,5 +94468,158 @@
"fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)"
}
]
+ },
+ {
+ "id": "a2185b99a21f",
+ "title": "Design Competition #38 — Palette & Type Mad-Lab",
+ "prompt": "Build this as one complete, self-contained HTML file: A palette + type 'mad scientist lab' where you mix two seed colors and a mood to brew a full token set, preview it live on a sample product card, copy the CSS variables, and hit 'randomize a happy accident'. 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": "2026-09-26T17:16:37.454Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "exo__glm-4-7-8bit-gs32",
+ "status": "error",
+ "error": "timeout after 300s",
+ "seconds": 300,
+ "cost": null,
+ "started_at": "2026-09-26T17:16:37.790Z",
+ "finished_at": "2026-09-26T17:21:37.946Z",
+ "queued_at": "2026-09-26T17:16:37.502Z",
+ "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)"
+ },
+ {
+ "model": "exo__glm-5-1",
+ "status": "error",
+ "error": "server restarted mid-run",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-26T17:21:37.995Z",
+ "finished_at": null,
+ "queued_at": "2026-09-26T17:16:37.552Z",
+ "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)",
+ "resumes": 1
+ },
+ {
+ "model": "exo__kimi-k2-5",
+ "status": "error",
+ "error": "server restarted mid-run",
+ "seconds": 0,
+ "cost": null,
+ "started_at": null,
+ "finished_at": null,
+ "queued_at": "2026-09-26T17:16:37.599Z",
+ "resumes": 1
+ },
+ {
+ "model": "exo__qwen3-5-397b-a17b-8bit",
+ "status": "error",
+ "error": "server restarted mid-run",
+ "seconds": 0,
+ "cost": null,
+ "started_at": null,
+ "finished_at": null,
+ "queued_at": "2026-09-26T17:16:37.654Z",
+ "resumes": 1
+ },
+ {
+ "model": "exo__minimax-m2-7-5bit",
+ "status": "error",
+ "error": "server restarted mid-run",
+ "seconds": 0,
+ "cost": null,
+ "started_at": null,
+ "finished_at": null,
+ "queued_at": "2026-09-26T17:16:37.705Z",
+ "resumes": 1
+ },
+ {
+ "model": "exo__qwen3-5-2b-mlx-8bit",
+ "status": "error",
+ "error": "server restarted mid-run",
+ "seconds": 0,
+ "cost": null,
+ "started_at": null,
+ "finished_at": null,
+ "queued_at": "2026-09-26T17:16:37.738Z",
+ "resumes": 1
+ }
+ ],
+ "aiPick": null
+ },
+ {
+ "id": "cabd046a58b0",
+ "title": "Art Competition #77 — Deep-Sea Fractal Dive",
+ "prompt": "Build this as one complete, self-contained HTML file: A fractal explorer disguised as a deep-sea dive: descend into a Julia set as if sinking through bioluminescent water, a depth gauge ticking, the palette cooling with depth, and a 'creature spotted' note at interesting zoom levels. 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": "2026-09-26T17:28:50.113Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "exo__deepseek-v3-2-8bit",
+ "status": "error",
+ "error": "timeout after 300s",
+ "seconds": 300,
+ "cost": null,
+ "started_at": "2026-09-26T17:28:51.078Z",
+ "finished_at": "2026-09-26T17:33:51.590Z",
+ "queued_at": "2026-09-26T17:28:50.323Z",
+ "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)"
+ },
+ {
+ "model": "exo__qwen3-5-27b-4bit",
+ "status": "error",
+ "error": "timeout after 300s",
+ "seconds": 300,
+ "cost": null,
+ "started_at": "2026-09-26T17:33:51.634Z",
+ "finished_at": "2026-09-26T17:38:51.755Z",
+ "queued_at": "2026-09-26T17:28:50.451Z",
+ "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)"
+ },
+ {
+ "model": "exo__gemma-4-e2b-it-8bit",
+ "status": "running",
+ "error": null,
+ "seconds": null,
+ "cost": null,
+ "started_at": "2026-09-26T17:38:51.802Z",
+ "finished_at": null,
+ "queued_at": "2026-09-26T17:28:50.579Z",
+ "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)"
+ },
+ {
+ "model": "exo__qwen3-coder-next-5bit",
+ "status": "queued",
+ "error": null,
+ "seconds": null,
+ "cost": null,
+ "started_at": null,
+ "finished_at": null,
+ "queued_at": "2026-09-26T17:28:50.705Z"
+ },
+ {
+ "model": "exo__glm-4-7-flash-4bit",
+ "status": "queued",
+ "error": null,
+ "seconds": null,
+ "cost": null,
+ "started_at": null,
+ "finished_at": null,
+ "queued_at": "2026-09-26T17:28:50.838Z"
+ },
+ {
+ "model": "exo__qwen3-6-35b-a3b-8bit",
+ "status": "queued",
+ "error": null,
+ "seconds": null,
+ "cost": null,
+ "started_at": null,
+ "finished_at": null,
+ "queued_at": "2026-09-26T17:28:50.949Z"
+ }
+ ]
}
]
\ No newline at end of file
diff --git a/yolo/arena-loop-state.json b/yolo/arena-loop-state.json
index dccae08..b8d6884 100644
--- a/yolo/arena-loop-state.json
+++ b/yolo/arena-loop-state.json
@@ -1 +1 @@
-{"promptIdx":3,"modelOffset":32,"compCount":{"Art":76,"Culture":75,"News":75,"Political Cartoon":75,"Games":38,"Real Work":38,"Data Viz":38,"Science":38,"Music":38,"Sports":38,"History":38,"Nature & Space":38,"Comedy":38,"Demoscene":38,"Finance":38,"Design":37},"catIdx":15,"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":1}}
\ No newline at end of file
+{"promptIdx":3,"modelOffset":44,"compCount":{"Art":77,"Culture":75,"News":75,"Political Cartoon":75,"Games":38,"Real Work":38,"Data Viz":38,"Science":38,"Music":38,"Sports":38,"History":38,"Nature & Space":38,"Comedy":38,"Demoscene":38,"Finance":38,"Design":38},"catIdx":17,"perCat":{"Art":4,"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 fcda840..75ff37b 100644
--- a/yolo/daily-log.jsonl
+++ b/yolo/daily-log.jsonl
@@ -852,3 +852,4 @@
{"ts":"2026-09-26T15:52:16.810Z","id":"f630bc9a0deb","promptId":"excuse","category":"Comedy","title":"Comedy Competition #38 — The Excuse Slot Machine","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
{"ts":"2026-09-26T16:28:48.552Z","id":"b1f41a3c67fc","promptId":"tunnel","category":"Demoscene","title":"Demoscene Competition #38 — Wormhole to Anywhere","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
{"ts":"2026-09-26T17:11:37.381Z","id":"07410865575d","promptId":"candles","category":"Finance","title":"Finance Competition #38 — Meme-Stock Chart With a Personality","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-26T17:23:50.055Z","id":"a2185b99a21f","promptId":"tokens","category":"Design","title":"Design Competition #38 — Palette & Type Mad-Lab","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
← 00ee8c5 auto-data-snapshot: 2026-09-26T10:11:45 (2 data files) — dat
·
back to Model Arena
·
auto-data-snapshot: 2026-09-26T11:13:09 (3 data files) — dat 9264bcd →