← back to Model Arena
auto-data-snapshot: 2026-09-27T19:27:44 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl
d37aa032febdbfc6f94f04961bd702dc608019b0 · 2026-09-27 19:28:17 -0700 · auto-commit-fleet
Files touched
M data/challenges.jsonM yolo/arena-loop-state.jsonM yolo/daily-log.jsonl
Diff
commit d37aa032febdbfc6f94f04961bd702dc608019b0
Author: auto-commit-fleet <steve@designerwallcoverings.com>
Date: Sun Sep 27 19:28:17 2026 -0700
auto-data-snapshot: 2026-09-27T19:27:44 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl
---
data/challenges.json | 96 +++++++++++++++++++++++++++++++++++++++++-----
yolo/arena-loop-state.json | 2 +-
yolo/daily-log.jsonl | 1 +
3 files changed, 88 insertions(+), 11 deletions(-)
diff --git a/data/challenges.json b/data/challenges.json
index 0a7eb3a..327401b 100644
--- a/data/challenges.json
+++ b/data/challenges.json
@@ -98828,54 +98828,130 @@
},
{
"model": "exo__gemma-4-e4b-it-bf16",
+ "status": "error",
+ "error": "timeout after 300s",
+ "seconds": 300,
+ "cost": null,
+ "started_at": "2026-09-28T01:54:53.877Z",
+ "finished_at": "2026-09-28T01:59:54.256Z",
+ "queued_at": "2026-09-28T01:49:53.275Z",
+ "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3-30B-A3B-Instruct-2507-4bit)"
+ },
+ {
+ "model": "exo__qwen3-5-397b-a17b-4bit",
+ "status": "error",
+ "error": "timeout after 300s",
+ "seconds": 300,
+ "cost": null,
+ "started_at": "2026-09-28T01:59:54.324Z",
+ "finished_at": "2026-09-28T02:04:54.643Z",
+ "queued_at": "2026-09-28T01:49:53.379Z",
+ "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3-30B-A3B-Instruct-2507-4bit)"
+ },
+ {
+ "model": "exo__glm-4-5-air-bf16",
+ "status": "error",
+ "error": "timeout after 300s",
+ "seconds": 300,
+ "cost": null,
+ "started_at": "2026-09-28T02:04:54.738Z",
+ "finished_at": "2026-09-28T02:09:55.245Z",
+ "queued_at": "2026-09-28T01:49:53.477Z",
+ "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3-30B-A3B-Instruct-2507-4bit)"
+ },
+ {
+ "model": "exo__qwen3-next-80b-a3b-instruct-4bit",
+ "status": "error",
+ "error": "timeout after 300s",
+ "seconds": 301,
+ "cost": null,
+ "started_at": "2026-09-28T02:09:55.305Z",
+ "finished_at": "2026-09-28T02:14:55.928Z",
+ "queued_at": "2026-09-28T01:49:53.521Z",
+ "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3-Next-80B-A3B-Instruct-4bit)"
+ },
+ {
+ "model": "exo__nvidia-nemotron-3-nano-30b-a3b-nvfp4",
+ "status": "error",
+ "error": "timeout after 300s",
+ "seconds": 303,
+ "cost": null,
+ "started_at": "2026-09-28T02:14:56.288Z",
+ "finished_at": "2026-09-28T02:19:59.324Z",
+ "queued_at": "2026-09-28T01:49:53.559Z",
+ "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3-30B-A3B-Instruct-2507-4bit)"
+ }
+ ]
+ },
+ {
+ "id": "ddcca631c6b6",
+ "title": "Comedy Competition #41 — The Excuse Slot Machine",
+ "prompt": "Build this as one complete, self-contained HTML file: An 'Excuse Engine' slot machine that spins three reels (who / what / cosmic reason) into gloriously implausible excuses, with a believability meter, a 'too far' lever, favorites, and copy-to-clipboard. 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": "Comedy",
+ "designTools": false,
+ "created_at": "2026-09-28T02:25:02.904Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "exo__qwen3-6-27b-8bit",
"status": "running",
"error": null,
"seconds": null,
"cost": null,
- "started_at": "2026-09-28T01:54:53.877Z",
+ "started_at": "2026-09-28T02:25:03.209Z",
"finished_at": null,
- "queued_at": "2026-09-28T01:49:53.275Z",
+ "queued_at": "2026-09-28T02:25:02.958Z",
"fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3-30B-A3B-Instruct-2507-4bit)"
},
{
- "model": "exo__qwen3-5-397b-a17b-4bit",
+ "model": "exo__llama-3-3-70b-instruct-8bit",
"status": "queued",
"error": null,
"seconds": null,
"cost": null,
"started_at": null,
"finished_at": null,
- "queued_at": "2026-09-28T01:49:53.379Z"
+ "queued_at": "2026-09-28T02:25:02.999Z"
},
{
- "model": "exo__glm-4-5-air-bf16",
+ "model": "exo__glm-5-1-mxfp4-q8",
"status": "queued",
"error": null,
"seconds": null,
"cost": null,
"started_at": null,
"finished_at": null,
- "queued_at": "2026-09-28T01:49:53.477Z"
+ "queued_at": "2026-09-28T02:25:03.037Z"
},
{
- "model": "exo__qwen3-next-80b-a3b-instruct-4bit",
+ "model": "exo__qwen3-coder-480b-a35b-instruct-8bit",
"status": "queued",
"error": null,
"seconds": null,
"cost": null,
"started_at": null,
"finished_at": null,
- "queued_at": "2026-09-28T01:49:53.521Z"
+ "queued_at": "2026-09-28T02:25:03.077Z"
},
{
- "model": "exo__nvidia-nemotron-3-nano-30b-a3b-nvfp4",
+ "model": "exo__minimax-m2-5-6bit",
+ "status": "queued",
+ "error": null,
+ "seconds": null,
+ "cost": null,
+ "started_at": null,
+ "finished_at": null,
+ "queued_at": "2026-09-28T02:25:03.121Z"
+ },
+ {
+ "model": "exo__minimax-m2-7-8bit",
"status": "queued",
"error": null,
"seconds": null,
"cost": null,
"started_at": null,
"finished_at": null,
- "queued_at": "2026-09-28T01:49:53.559Z"
+ "queued_at": "2026-09-28T02:25:03.162Z"
}
]
}
diff --git a/yolo/arena-loop-state.json b/yolo/arena-loop-state.json
index 425b2b5..181fcdf 100644
--- a/yolo/arena-loop-state.json
+++ b/yolo/arena-loop-state.json
@@ -1 +1 @@
-{"promptIdx":3,"modelOffset":112,"compCount":{"Art":82,"Culture":81,"News":81,"Political Cartoon":81,"Games":41,"Real Work":41,"Data Viz":41,"Science":41,"Music":41,"Sports":41,"History":41,"Nature & Space":41,"Comedy":40,"Demoscene":40,"Finance":40,"Design":40},"catIdx":12,"perCat":{"Art":1,"Culture":1,"News":1,"Political Cartoon":1,"Games":2,"Real Work":2,"Data Viz":2,"Science":2,"Music":2,"Sports":2,"History":2,"Nature & Space":2,"Comedy":1,"Demoscene":1,"Finance":1,"Design":1}}
\ No newline at end of file
+{"promptIdx":3,"modelOffset":118,"compCount":{"Art":82,"Culture":81,"News":81,"Political Cartoon":81,"Games":41,"Real Work":41,"Data Viz":41,"Science":41,"Music":41,"Sports":41,"History":41,"Nature & Space":41,"Comedy":41,"Demoscene":40,"Finance":40,"Design":40},"catIdx":13,"perCat":{"Art":1,"Culture":1,"News":1,"Political Cartoon":1,"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
diff --git a/yolo/daily-log.jsonl b/yolo/daily-log.jsonl
index c4a7263..879539d 100644
--- a/yolo/daily-log.jsonl
+++ b/yolo/daily-log.jsonl
@@ -907,3 +907,4 @@
{"ts":"2026-09-28T00:50:54.523Z","id":"05e5fa452757","promptId":"synth","category":"Music","title":"Music Competition #41 — The Singing Creature Synth","models":6,"done":0,"errored":0,"settled":false,"aiPick":null,"loop":true}
{"ts":"2026-09-28T01:10:19.976Z","id":"57d8f565079d","promptId":"bracket","category":"Sports","title":"Sports Competition #41 — Mascot Clash Bracket","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
{"ts":"2026-09-28T01:44:53.007Z","id":"98cfc5a1ebdc","promptId":"empire-map","category":"History","title":"History Competition #41 — An Empire That Breathes","models":6,"done":1,"errored":5,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-28T02:20:02.798Z","id":"c16b6f43d022","promptId":"ecosystem","category":"Nature & Space","title":"Nature & Space Competition #41 — Terrarium in a Jar","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
← 5b54efa auto-data-snapshot: 2026-09-27T18:56:55 (3 data files) — dat
·
back to Model Arena
·
auto-data-snapshot: 2026-09-27T19:58:22 (2 data files) — dat e1f90d5 →