← back to Model Arena
auto-data-snapshot: 2026-09-27T05:34:27 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl
9d5f935a1539d97798f17180116fb95ec06f255d · 2026-09-27 05:34:54 -0700 · auto-commit-fleet
Files touched
M data/challenges.jsonM yolo/arena-loop-state.jsonM yolo/daily-log.jsonl
Diff
commit 9d5f935a1539d97798f17180116fb95ec06f255d
Author: auto-commit-fleet <steve@designerwallcoverings.com>
Date: Sun Sep 27 05:34:54 2026 -0700
auto-data-snapshot: 2026-09-27T05:34:27 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl
---
data/challenges.json | 92 ++++++++++++++++++++++++++++++++++++++++++----
yolo/arena-loop-state.json | 2 +-
yolo/daily-log.jsonl | 1 +
3 files changed, 86 insertions(+), 9 deletions(-)
diff --git a/data/challenges.json b/data/challenges.json
index 30ea729..5c88899 100644
--- a/data/challenges.json
+++ b/data/challenges.json
@@ -97181,44 +97181,120 @@
},
{
"model": "exo__gemma-4-e4b-it-bf16",
+ "status": "error",
+ "error": "timeout after 300s",
+ "seconds": 301,
+ "cost": null,
+ "started_at": "2026-09-27T12:03:26.642Z",
+ "finished_at": "2026-09-27T12:08:27.888Z",
+ "queued_at": "2026-09-27T11:53:25.094Z",
+ "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)"
+ },
+ {
+ "model": "exo__qwen3-5-397b-a17b-4bit",
+ "status": "error",
+ "error": "timeout after 300s",
+ "seconds": 300,
+ "cost": null,
+ "started_at": "2026-09-27T12:08:28.223Z",
+ "finished_at": "2026-09-27T12:13:28.663Z",
+ "queued_at": "2026-09-27T11:53:25.161Z",
+ "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)"
+ },
+ {
+ "model": "exo__glm-4-5-air-bf16",
+ "status": "error",
+ "error": "timeout after 300s",
+ "seconds": 300,
+ "cost": null,
+ "started_at": "2026-09-27T12:13:28.769Z",
+ "finished_at": "2026-09-27T12:18:29.226Z",
+ "queued_at": "2026-09-27T11:53:25.223Z",
+ "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)"
+ },
+ {
+ "model": "exo__qwen3-next-80b-a3b-instruct-4bit",
+ "status": "error",
+ "error": "timeout after 300s",
+ "seconds": 300,
+ "cost": null,
+ "started_at": "2026-09-27T12:18:29.364Z",
+ "finished_at": "2026-09-27T12:23:29.662Z",
+ "queued_at": "2026-09-27T11:53:25.279Z",
+ "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3-Next-80B-A3B-Instruct-4bit)"
+ }
+ ]
+ },
+ {
+ "id": "3059bd8fe2e0",
+ "title": "History Competition #40 — Walk-Through Age of Invention",
+ "prompt": "Build this as one complete, self-contained HTML file: A scrollable timeline of an INVENTED age of invention where each era is a room you walk through, gadgets you can click to 'switch on', and a filter that dims everything except one thread of progress. 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": "History",
+ "designTools": false,
+ "created_at": "2026-09-27T12:28:30.414Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "exo__nvidia-nemotron-3-nano-30b-a3b-nvfp4",
+ "status": "error",
+ "error": "timeout after 300s",
+ "seconds": 300,
+ "cost": null,
+ "started_at": "2026-09-27T12:28:31.818Z",
+ "finished_at": "2026-09-27T12:33:32.285Z",
+ "queued_at": "2026-09-27T12:28:30.607Z",
+ "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)"
+ },
+ {
+ "model": "exo__qwen3-6-27b-8bit",
"status": "running",
"error": null,
"seconds": null,
"cost": null,
- "started_at": "2026-09-27T12:03:26.642Z",
+ "started_at": "2026-09-27T12:33:32.762Z",
"finished_at": null,
- "queued_at": "2026-09-27T11:53:25.094Z",
+ "queued_at": "2026-09-27T12:28:30.834Z",
"fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)"
},
{
- "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": "2026-09-27T11:53:25.161Z"
+ "queued_at": "2026-09-27T12:28:30.995Z"
},
{
- "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": "2026-09-27T11:53:25.223Z"
+ "queued_at": "2026-09-27T12:28:31.191Z"
},
{
- "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": "2026-09-27T12:28:31.360Z"
+ },
+ {
+ "model": "exo__minimax-m2-5-6bit",
"status": "queued",
"error": null,
"seconds": null,
"cost": null,
"started_at": null,
"finished_at": null,
- "queued_at": "2026-09-27T11:53:25.279Z"
+ "queued_at": "2026-09-27T12:28:31.647Z"
}
]
}
diff --git a/yolo/arena-loop-state.json b/yolo/arena-loop-state.json
index 1803a71..c15ded9 100644
--- a/yolo/arena-loop-state.json
+++ b/yolo/arena-loop-state.json
@@ -1 +1 @@
-{"promptIdx":3,"modelOffset":111,"compCount":{"Art":80,"Culture":79,"News":79,"Political Cartoon":79,"Games":40,"Real Work":40,"Data Viz":40,"Science":40,"Music":40,"Sports":40,"History":39,"Nature & Space":39,"Comedy":39,"Demoscene":39,"Finance":39,"Design":39},"catIdx":10,"perCat":{"Art":3,"Culture":3,"News":3,"Political Cartoon":3,"Games":1,"Real Work":1,"Data Viz":1,"Science":1,"Music":1,"Sports":1,"History":3,"Nature & Space":3,"Comedy":3,"Demoscene":3,"Finance":3,"Design":3}}
\ No newline at end of file
+{"promptIdx":3,"modelOffset":117,"compCount":{"Art":80,"Culture":79,"News":79,"Political Cartoon":79,"Games":40,"Real Work":40,"Data Viz":40,"Science":40,"Music":40,"Sports":40,"History":40,"Nature & Space":39,"Comedy":39,"Demoscene":39,"Finance":39,"Design":39},"catIdx":11,"perCat":{"Art":3,"Culture":3,"News":3,"Political Cartoon":3,"Games":1,"Real Work":1,"Data Viz":1,"Science":1,"Music":1,"Sports":1,"History":1,"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 27f0a52..d2b9161 100644
--- a/yolo/daily-log.jsonl
+++ b/yolo/daily-log.jsonl
@@ -887,3 +887,4 @@
{"ts":"2026-09-27T10:37:56.992Z","id":"93648dcc38ff","promptId":"multi-chart","category":"Data Viz","title":"Data Viz Competition #40 — City of Data Dashboard","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
{"ts":"2026-09-27T11:13:11.050Z","id":"403b88e8b45b","promptId":"solar","category":"Science","title":"Science Competition #40 — Conduct the Solar System","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
{"ts":"2026-09-27T11:48:24.689Z","id":"53971a0c131a","promptId":"sequencer","category":"Music","title":"Music Competition #40 — Constellation Sequencer","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-27T12:23:30.333Z","id":"f69c027db6a5","promptId":"standings","category":"Sports","title":"Sports Competition #40 — Zero-G Relay League","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
← 39b568d auto-data-snapshot: 2026-09-27T05:03:58 (3 data files) — dat
·
back to Model Arena
·
auto-data-snapshot: 2026-09-27T06:04:59 (3 data files) — dat cfdf7a9 →