← back to Model Arena
auto-data-snapshot: 2026-09-26T09:21:27 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl
4b88d13f3fd4b57c10acfa5746e595c606791258 · 2026-09-26 09:23:46 -0700 · auto-commit-fleet
Files touched
M data/challenges.jsonM yolo/arena-loop-state.jsonM yolo/daily-log.jsonl
Diff
commit 4b88d13f3fd4b57c10acfa5746e595c606791258
Author: auto-commit-fleet <steve@designerwallcoverings.com>
Date: Sat Sep 26 09:23:46 2026 -0700
auto-data-snapshot: 2026-09-26T09:21:27 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl
---
data/challenges.json | 131 ++++++++++++++++++++++++++++++++++++---------
yolo/arena-loop-state.json | 2 +-
yolo/daily-log.jsonl | 1 +
3 files changed, 109 insertions(+), 25 deletions(-)
diff --git a/data/challenges.json b/data/challenges.json
index 6cc3119..f141b11 100644
--- a/data/challenges.json
+++ b/data/challenges.json
@@ -94154,7 +94154,7 @@
"finished_at": null,
"queued_at": "2026-09-26T15:38:20.429Z",
"fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3-30B-A3B-Instruct-2507-4bit)",
- "resumes": 3
+ "resumes": 4
},
{
"model": "mac1__qwen2-5vl-7b",
@@ -94176,7 +94176,7 @@
"started_at": "2026-09-26T15:38:21.127Z",
"finished_at": null,
"queued_at": "2026-09-26T15:38:20.638Z",
- "resumes": 3
+ "resumes": 4
},
{
"model": "exo__gemma-4-26b-a4b-it-6bit",
@@ -94187,7 +94187,7 @@
"started_at": null,
"finished_at": null,
"queued_at": "2026-09-26T15:38:20.712Z",
- "resumes": 3
+ "resumes": 4
},
{
"model": "exo__qwen3-6-35b-a3b-bf16",
@@ -94198,7 +94198,7 @@
"started_at": null,
"finished_at": null,
"queued_at": "2026-09-26T15:38:20.745Z",
- "resumes": 3
+ "resumes": 4
},
{
"model": "exo__qwen3-vl-4b-instruct-4bit",
@@ -94209,7 +94209,7 @@
"started_at": null,
"finished_at": null,
"queued_at": "2026-09-26T15:38:20.825Z",
- "resumes": 3
+ "resumes": 4
}
],
"aiPick": null
@@ -94258,54 +94258,137 @@
},
{
"model": "exo__llama-3-3-70b-instruct-4bit",
- "status": "running",
- "error": null,
- "seconds": null,
+ "status": "error",
+ "error": "server restarted mid-run",
+ "seconds": 0,
"cost": null,
"started_at": "2026-09-26T15:50:52.257Z",
"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)"
+ "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3-30B-A3B-Instruct-2507-4bit)",
+ "resumes": 1
},
{
"model": "exo__gemma-4-e2b-it-bf16",
- "status": "queued",
- "error": null,
- "seconds": null,
+ "status": "error",
+ "error": "server restarted mid-run",
+ "seconds": 0,
"cost": null,
"started_at": null,
"finished_at": null,
- "queued_at": "2026-09-26T15:45:49.924Z"
+ "queued_at": "2026-09-26T15:45:49.924Z",
+ "resumes": 1
},
{
"model": "exo__qwen3-next-80b-a3b-instruct-8bit",
- "status": "queued",
- "error": null,
- "seconds": null,
+ "status": "error",
+ "error": "server restarted mid-run",
+ "seconds": 0,
"cost": null,
"started_at": null,
"finished_at": null,
- "queued_at": "2026-09-26T15:45:50.215Z"
+ "queued_at": "2026-09-26T15:45:50.215Z",
+ "resumes": 1
},
{
"model": "exo__qwen3-6-27b-4bit",
- "status": "queued",
- "error": null,
- "seconds": null,
+ "status": "error",
+ "error": "server restarted mid-run",
+ "seconds": 0,
"cost": null,
"started_at": null,
"finished_at": null,
- "queued_at": "2026-09-26T15:45:50.352Z"
+ "queued_at": "2026-09-26T15:45:50.352Z",
+ "resumes": 1
},
{
"model": "exo__glm-4-7-4bit",
- "status": "queued",
+ "status": "error",
+ "error": "server restarted mid-run",
+ "seconds": 0,
+ "cost": null,
+ "started_at": null,
+ "finished_at": null,
+ "queued_at": "2026-09-26T15:45:50.626Z",
+ "resumes": 1
+ }
+ ],
+ "aiPick": null
+ },
+ {
+ "id": "b1f41a3c67fc",
+ "title": "Demoscene Competition #38 — Wormhole to Anywhere",
+ "prompt": "Build this as one complete, self-contained HTML file: An infinite tunnel that flies through an INVENTED wormhole to shifting destinations (neon city, coral reef, circuit board) selectable on the fly, with texture/palette controls and auto-motion. 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": "2026-09-26T15:57:16.993Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "exo__gemma-4-31b-it-4bit",
+ "status": "error",
+ "error": "timeout after 300s",
+ "seconds": 301,
+ "cost": null,
+ "started_at": "2026-09-26T15:57:17.765Z",
+ "finished_at": "2026-09-26T16:02:19.252Z",
+ "queued_at": "2026-09-26T15:57:17.094Z",
+ "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3-30B-A3B-Instruct-2507-4bit)"
+ },
+ {
+ "model": "exo__nvidia-nemotron-3-nano-30b-a3b-mlx-4bit",
+ "status": "error",
+ "error": "timeout after 300s",
+ "seconds": 300,
+ "cost": null,
+ "started_at": "2026-09-26T16:02:19.440Z",
+ "finished_at": "2026-09-26T16:07:19.836Z",
+ "queued_at": "2026-09-26T15:57:17.312Z",
+ "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3-30B-A3B-Instruct-2507-4bit)"
+ },
+ {
+ "model": "exo__llama-3-1-nemotron-nano-4b-v1-1-4bit",
+ "status": "error",
+ "error": "timeout after 300s",
+ "seconds": 300,
+ "cost": null,
+ "started_at": "2026-09-26T16:07:20.021Z",
+ "finished_at": "2026-09-26T16:12:20.451Z",
+ "queued_at": "2026-09-26T15:57:17.369Z",
+ "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3-30B-A3B-Instruct-2507-4bit)"
+ },
+ {
+ "model": "exo__qwen3-coder-next-6bit",
+ "status": "error",
+ "error": "timeout after 300s",
+ "seconds": 301,
+ "cost": null,
+ "started_at": "2026-09-26T16:12:20.556Z",
+ "finished_at": "2026-09-26T16:17:21.231Z",
+ "queued_at": "2026-09-26T15:57:17.436Z",
+ "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3-30B-A3B-Instruct-2507-4bit)"
+ },
+ {
+ "model": "exo__step-3-5-flash-6bit",
+ "status": "error",
+ "error": "timeout after 300s",
+ "seconds": 323,
+ "cost": null,
+ "started_at": "2026-09-26T16:17:26.619Z",
+ "finished_at": "2026-09-26T16:22:50.135Z",
+ "queued_at": "2026-09-26T15:57:17.480Z",
+ "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3-30B-A3B-Instruct-2507-4bit)"
+ },
+ {
+ "model": "exo__qwen3-next-80b-a3b-thinking-4bit",
+ "status": "running",
"error": null,
"seconds": null,
"cost": null,
- "started_at": null,
+ "started_at": "2026-09-26T16:22:54.146Z",
"finished_at": null,
- "queued_at": "2026-09-26T15:45:50.626Z"
+ "queued_at": "2026-09-26T15:57:17.601Z",
+ "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3-30B-A3B-Instruct-2507-4bit)"
}
]
}
diff --git a/yolo/arena-loop-state.json b/yolo/arena-loop-state.json
index eedc5d6..196ab07 100644
--- a/yolo/arena-loop-state.json
+++ b/yolo/arena-loop-state.json
@@ -1 +1 @@
-{"promptIdx":3,"modelOffset":20,"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":37,"Finance":37,"Design":37},"catIdx":13,"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":1,"Finance":1,"Design":1}}
\ No newline at end of file
+{"promptIdx":3,"modelOffset":26,"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":37,"Design":37},"catIdx":14,"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":1,"Design":1}}
\ No newline at end of file
diff --git a/yolo/daily-log.jsonl b/yolo/daily-log.jsonl
index 853b10c..de2f10b 100644
--- a/yolo/daily-log.jsonl
+++ b/yolo/daily-log.jsonl
@@ -849,3 +849,4 @@
{"ts":"2026-09-25T21:37:54.450Z","id":"f296e08eb20c","promptId":"synth","category":"Music","title":"Music Competition #38 — The Singing Creature Synth","models":4,"done":4,"errored":0,"settled":true,"aiPick":null,"loop":true}
{"ts":"2026-09-26T15:33:19.496Z","id":"53923fadf112","promptId":"empire-map","category":"History","title":"History Competition #38 — An Empire That Breathes","models":6,"done":2,"errored":4,"settled":true,"aiPick":null,"loop":true}
{"ts":"2026-09-26T15:40:44.983Z","id":"58f3c99d2354","promptId":"ecosystem","category":"Nature & Space","title":"Nature & Space Competition #38 — Terrarium in a Jar","models":6,"done":1,"errored":5,"settled":true,"aiPick":null,"loop":true}
+{"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}
← 8d2c52a fix(TK-12121): exit on EADDRINUSE (single-owner guard) + thu
·
back to Model Arena
·
auto-data-snapshot: 2026-09-26T09:40:15 (3 data files) — dat 9c83215 →