← back to Model Arena
auto-data-snapshot: 2026-09-27T18:56:55 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl
5b54efa8fc99ba07e23c7e08f47bd32b4fc72a06 · 2026-09-27 18:57:29 -0700 · auto-commit-fleet
Files touched
M data/challenges.jsonM yolo/arena-loop-state.jsonM yolo/daily-log.jsonl
Diff
commit 5b54efa8fc99ba07e23c7e08f47bd32b4fc72a06
Author: auto-commit-fleet <steve@designerwallcoverings.com>
Date: Sun Sep 27 18:57:29 2026 -0700
auto-data-snapshot: 2026-09-27T18:56:55 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl
---
data/challenges.json | 99 ++++++++++++++++++++++++++++++++++++++++++----
yolo/arena-loop-state.json | 2 +-
yolo/daily-log.jsonl | 1 +
3 files changed, 93 insertions(+), 9 deletions(-)
diff --git a/data/challenges.json b/data/challenges.json
index d09a282..0a7eb3a 100644
--- a/data/challenges.json
+++ b/data/challenges.json
@@ -98755,44 +98755,127 @@
},
{
"model": "exo__kimi-k2-thinking",
+ "status": "error",
+ "error": "timeout after 300s",
+ "seconds": 300,
+ "cost": null,
+ "started_at": "2026-09-28T01:25:21.885Z",
+ "finished_at": "2026-09-28T01:30:22.324Z",
+ "queued_at": "2026-09-28T01:15:20.648Z",
+ "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3-30B-A3B-Instruct-2507-4bit)"
+ },
+ {
+ "model": "exo__qwen3-coder-next-bf16",
+ "status": "done",
+ "error": null,
+ "seconds": 263,
+ "cost": 0,
+ "started_at": "2026-09-28T01:30:22.499Z",
+ "finished_at": "2026-09-28T01:34:45.164Z",
+ "queued_at": "2026-09-28T01:15:20.734Z",
+ "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3-30B-A3B-Instruct-2507-4bit)",
+ "bytes": 20855,
+ "thumb": true,
+ "aiScore": null,
+ "aiReason": "judge failed: all vision panelists failed"
+ },
+ {
+ "model": "exo__deepseek-v3-2-4bit",
+ "status": "error",
+ "error": "timeout after 300s",
+ "seconds": 300,
+ "cost": null,
+ "started_at": "2026-09-28T01:34:45.230Z",
+ "finished_at": "2026-09-28T01:39:45.465Z",
+ "queued_at": "2026-09-28T01:15:20.866Z",
+ "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3-30B-A3B-Instruct-2507-4bit)"
+ },
+ {
+ "model": "exo__nvidia-nemotron-nano-9b-v2-6bit",
+ "status": "error",
+ "error": "timeout after 300s",
+ "seconds": 300,
+ "cost": null,
+ "started_at": "2026-09-28T01:39:45.503Z",
+ "finished_at": "2026-09-28T01:44:45.705Z",
+ "queued_at": "2026-09-28T01:15:20.962Z",
+ "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3-30B-A3B-Instruct-2507-4bit)"
+ }
+ ],
+ "judging": false,
+ "aiPick": null,
+ "judged_at": "2026-09-28T01:44:45.822Z"
+ },
+ {
+ "id": "c16b6f43d022",
+ "title": "Nature & Space Competition #41 — Terrarium in a Jar",
+ "prompt": "Build this as one complete, self-contained HTML file: A jar-terrarium ecosystem of INVENTED critters with live population graphs — feed them, introduce a predator, or trigger a drought and watch the food web wobble toward chaos or balance, with a reset. 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": "Nature & Space",
+ "designTools": false,
+ "created_at": "2026-09-28T01:49:53.144Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "exo__meta-llama-3-1-8b-instruct-bf16",
+ "status": "error",
+ "error": "timeout after 300s",
+ "seconds": 300,
+ "cost": null,
+ "started_at": "2026-09-28T01:49:53.598Z",
+ "finished_at": "2026-09-28T01:54:53.778Z",
+ "queued_at": "2026-09-28T01:49:53.190Z",
+ "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3-30B-A3B-Instruct-2507-4bit)"
+ },
+ {
+ "model": "exo__gemma-4-e4b-it-bf16",
"status": "running",
"error": null,
"seconds": null,
"cost": null,
- "started_at": "2026-09-28T01:25:21.885Z",
+ "started_at": "2026-09-28T01:54:53.877Z",
"finished_at": null,
- "queued_at": "2026-09-28T01:15:20.648Z",
+ "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-coder-next-bf16",
+ "model": "exo__qwen3-5-397b-a17b-4bit",
"status": "queued",
"error": null,
"seconds": null,
"cost": null,
"started_at": null,
"finished_at": null,
- "queued_at": "2026-09-28T01:15:20.734Z"
+ "queued_at": "2026-09-28T01:49:53.379Z"
},
{
- "model": "exo__deepseek-v3-2-4bit",
+ "model": "exo__glm-4-5-air-bf16",
"status": "queued",
"error": null,
"seconds": null,
"cost": null,
"started_at": null,
"finished_at": null,
- "queued_at": "2026-09-28T01:15:20.866Z"
+ "queued_at": "2026-09-28T01:49:53.477Z"
},
{
- "model": "exo__nvidia-nemotron-nano-9b-v2-6bit",
+ "model": "exo__qwen3-next-80b-a3b-instruct-4bit",
+ "status": "queued",
+ "error": null,
+ "seconds": null,
+ "cost": null,
+ "started_at": null,
+ "finished_at": null,
+ "queued_at": "2026-09-28T01:49:53.521Z"
+ },
+ {
+ "model": "exo__nvidia-nemotron-3-nano-30b-a3b-nvfp4",
"status": "queued",
"error": null,
"seconds": null,
"cost": null,
"started_at": null,
"finished_at": null,
- "queued_at": "2026-09-28T01:15:20.962Z"
+ "queued_at": "2026-09-28T01:49:53.559Z"
}
]
}
diff --git a/yolo/arena-loop-state.json b/yolo/arena-loop-state.json
index d732518..425b2b5 100644
--- a/yolo/arena-loop-state.json
+++ b/yolo/arena-loop-state.json
@@ -1 +1 @@
-{"promptIdx":3,"modelOffset":106,"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":40,"Comedy":40,"Demoscene":40,"Finance":40,"Design":40},"catIdx":11,"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":1,"Comedy":1,"Demoscene":1,"Finance":1,"Design":1}}
\ No newline at end of file
+{"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
diff --git a/yolo/daily-log.jsonl b/yolo/daily-log.jsonl
index 346129c..c4a7263 100644
--- a/yolo/daily-log.jsonl
+++ b/yolo/daily-log.jsonl
@@ -906,3 +906,4 @@
{"ts":"2026-09-28T00:00:45.785Z","id":"1930befe0c60","promptId":"pendulum","category":"Science","title":"Science Competition #41 — The Painting Pendulum","models":6,"done":0,"errored":0,"settled":false,"aiPick":null,"loop":true}
{"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}
← e5f6ae4 auto-data-snapshot: 2026-09-27T18:26:05 (3 data files) — dat
·
back to Model Arena
·
auto-data-snapshot: 2026-09-27T19:27:44 (3 data files) — dat d37aa03 →