← back to Model Arena
auto-data-snapshot: 2026-09-18T20:12:47 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl
a45dd2308df2a54cafa327fbb5f3d90c0521f507 · 2026-09-18 20:13:58 -0700 · auto-commit-fleet
Files touched
M data/challenges.jsonM yolo/arena-loop-state.jsonM yolo/daily-log.jsonl
Diff
commit a45dd2308df2a54cafa327fbb5f3d90c0521f507
Author: auto-commit-fleet <steve@designerwallcoverings.com>
Date: Fri Sep 18 20:13:58 2026 -0700
auto-data-snapshot: 2026-09-18T20:12:47 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl
---
data/challenges.json | 198 ++++++++++++++++++++++++++++++++++++++++-----
yolo/arena-loop-state.json | 2 +-
yolo/daily-log.jsonl | 3 +
3 files changed, 183 insertions(+), 20 deletions(-)
diff --git a/data/challenges.json b/data/challenges.json
index 4953e9f..8040048 100644
--- a/data/challenges.json
+++ b/data/challenges.json
@@ -40704,12 +40704,12 @@
"runs": [
{
"model": "mlx__qwen3-30b-a3b-instruct-2507-4bit",
- "status": "running",
- "error": null,
- "seconds": null,
+ "status": "error",
+ "error": "timeout after 600s",
+ "seconds": 600,
"cost": null,
"started_at": "2026-09-19T02:41:50.364Z",
- "finished_at": null,
+ "finished_at": "2026-09-19T02:51:50.383Z",
"queued_at": "2026-09-19T02:41:50.321Z"
},
{
@@ -40724,22 +40724,26 @@
},
{
"model": "qwen25-7b",
- "status": "running",
+ "status": "done",
"error": null,
- "seconds": null,
- "cost": null,
+ "seconds": 40,
+ "cost": 0,
"started_at": "2026-09-19T02:41:50.375Z",
- "finished_at": null,
- "queued_at": "2026-09-19T02:41:50.341Z"
+ "finished_at": "2026-09-19T02:42:30.266Z",
+ "queued_at": "2026-09-19T02:41:50.341Z",
+ "bytes": 6147,
+ "thumb": true,
+ "aiScore": null,
+ "aiReason": "judge failed: all vision panelists failed"
},
{
"model": "mlx__qwen3-next-80b-a3b-instruct-4bit",
- "status": "queued",
- "error": null,
- "seconds": null,
+ "status": "error",
+ "error": "timeout after 600s",
+ "seconds": 600,
"cost": null,
- "started_at": null,
- "finished_at": null,
+ "started_at": "2026-09-19T02:51:50.400Z",
+ "finished_at": "2026-09-19T03:01:50.419Z",
"queued_at": "2026-09-19T02:41:50.347Z"
},
{
@@ -40754,13 +40758,169 @@
},
{
"model": "mac1__minicpm-v-latest",
- "status": "queued",
+ "status": "done",
"error": null,
- "seconds": null,
+ "seconds": 8,
+ "cost": 0,
+ "started_at": "2026-09-19T02:42:30.285Z",
+ "finished_at": "2026-09-19T02:42:37.807Z",
+ "queued_at": "2026-09-19T02:41:50.358Z",
+ "bytes": 347,
+ "thumb": true,
+ "aiScore": null,
+ "aiReason": "judge failed: all vision panelists failed"
+ }
+ ],
+ "judging": false,
+ "aiPick": null,
+ "judged_at": "2026-09-19T03:01:50.812Z"
+ },
+ {
+ "id": "8d9938674331",
+ "title": "Political Cartoon Competition #5 — The Seesaw Debate",
+ "prompt": "Build this as one complete, self-contained HTML file: An original SVG editorial cartoon about an INVENTED debate ('should robots get weekends?'): a seesaw of absurd figures the viewer can tip, with a caption that rewrites itself for each side. Non-partisan, invented symbols only. 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": "Political Cartoon",
+ "designTools": false,
+ "created_at": "2026-09-19T03:06:50.934Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "exo__qwen3-5-122b-a10b-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T03:06:50.997Z",
+ "finished_at": "2026-09-19T03:06:51.038Z",
+ "queued_at": "2026-09-19T03:06:50.956Z"
+ },
+ {
+ "model": "mac1__qwen2-5vl-7b",
+ "status": "done",
+ "error": null,
+ "seconds": 44,
+ "cost": 0,
+ "started_at": "2026-09-19T03:06:51.003Z",
+ "finished_at": "2026-09-19T03:07:35.143Z",
+ "queued_at": "2026-09-19T03:06:50.969Z",
+ "bytes": 6534,
+ "thumb": true,
+ "aiScore": null,
+ "aiReason": "judge failed: all vision panelists failed"
+ },
+ {
+ "model": "exo__gemma-4-26b-a4b-it-6bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T03:06:51.044Z",
+ "finished_at": "2026-09-19T03:06:51.082Z",
+ "queued_at": "2026-09-19T03:06:50.975Z"
+ },
+ {
+ "model": "exo__qwen3-6-35b-a3b-bf16",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T03:06:51.087Z",
+ "finished_at": "2026-09-19T03:06:51.125Z",
+ "queued_at": "2026-09-19T03:06:50.981Z"
+ },
+ {
+ "model": "exo__qwen3-vl-4b-instruct-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T03:06:51.133Z",
+ "finished_at": "2026-09-19T03:06:51.170Z",
+ "queued_at": "2026-09-19T03:06:50.987Z"
+ },
+ {
+ "model": "exo__minimax-m2-7",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T03:06:51.178Z",
+ "finished_at": "2026-09-19T03:06:51.221Z",
+ "queued_at": "2026-09-19T03:06:50.992Z"
+ }
+ ],
+ "judging": false,
+ "aiPick": null,
+ "judged_at": "2026-09-19T03:07:36.940Z"
+ },
+ {
+ "id": "f4ce66dbcea1",
+ "title": "Games Competition #3 — Tower on a Walking Giant",
+ "prompt": "Build this as one complete, self-contained HTML file: A block-stacker built on the back of a walking giant: each drop sways the tower with real wobble physics, wind gusts nudge your timing, and reaching cloud height unlocks a tiny weather system at the summit. 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": "Games",
+ "designTools": false,
+ "created_at": "2026-09-19T03:12:39.043Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "exo__llama-3-3-70b-instruct-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T03:12:39.110Z",
+ "finished_at": "2026-09-19T03:12:39.120Z",
+ "queued_at": "2026-09-19T03:12:39.064Z"
+ },
+ {
+ "model": "exo__gemma-4-e2b-it-bf16",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T03:12:39.129Z",
+ "finished_at": "2026-09-19T03:12:39.140Z",
+ "queued_at": "2026-09-19T03:12:39.075Z"
+ },
+ {
+ "model": "exo__qwen3-next-80b-a3b-instruct-8bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T03:12:39.148Z",
+ "finished_at": "2026-09-19T03:12:39.157Z",
+ "queued_at": "2026-09-19T03:12:39.082Z"
+ },
+ {
+ "model": "exo__qwen3-6-27b-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T03:12:39.163Z",
+ "finished_at": "2026-09-19T03:12:39.174Z",
+ "queued_at": "2026-09-19T03:12:39.089Z"
+ },
+ {
+ "model": "exo__glm-4-7-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T03:12:39.180Z",
+ "finished_at": "2026-09-19T03:12:39.190Z",
+ "queued_at": "2026-09-19T03:12:39.095Z"
+ },
+ {
+ "model": "exo__gemma-4-31b-it-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
"cost": null,
- "started_at": null,
- "finished_at": null,
- "queued_at": "2026-09-19T02:41:50.358Z"
+ "started_at": "2026-09-19T03:12:39.195Z",
+ "finished_at": "2026-09-19T03:12:39.205Z",
+ "queued_at": "2026-09-19T03:12:39.104Z"
}
]
}
diff --git a/yolo/arena-loop-state.json b/yolo/arena-loop-state.json
index 692d1be..2ecae13 100644
--- a/yolo/arena-loop-state.json
+++ b/yolo/arena-loop-state.json
@@ -1 +1 @@
-{"promptIdx":3,"modelOffset":7,"compCount":{"Art":6,"Culture":5,"News":5,"Political Cartoon":4,"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},"catIdx":3,"perCat":{"Art":1,"Culture":1,"News":1,"Political Cartoon":4,"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
+{"promptIdx":3,"modelOffset":19,"compCount":{"Art":6,"Culture":5,"News":5,"Political Cartoon":5,"Games":3,"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},"catIdx":5,"perCat":{"Art":1,"Culture":1,"News":1,"Political Cartoon":1,"Games":3,"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 7e8c19e..d515bd8 100644
--- a/yolo/daily-log.jsonl
+++ b/yolo/daily-log.jsonl
@@ -96,3 +96,6 @@
{"ts":"2026-09-19T02:24:01.902Z","id":"0fb5d35efc60","promptId":"civic-explainer","category":"Political Cartoon","title":"Political Cartoon Competition #4 — How a Law Gets Passed (Rube Goldberg)","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
{"ts":"2026-09-19T02:29:10.004Z","id":"151e740be516","promptId":"gen-art","category":"Art","title":"Art Competition #6 — Living Ink Canvas","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
{"ts":"2026-09-19T02:36:50.144Z","id":"a339bcf33204","promptId":"museum","category":"Culture","title":"Culture Competition #5 — Museum of a Lost Civilization","models":6,"done":1,"errored":5,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-19T03:01:50.873Z","id":"42a46ff18e1b","promptId":"election-viz","category":"News","title":"News Competition #5 — Election Night: Floating Isles","models":6,"done":2,"errored":4,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-19T03:07:39.017Z","id":"8d9938674331","promptId":"editorial-cartoon","category":"Political Cartoon","title":"Political Cartoon Competition #5 — The Seesaw Debate","models":6,"done":1,"errored":5,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-19T03:12:47.113Z","id":"f4ce66dbcea1","promptId":"tower","category":"Games","title":"Games Competition #3 — Tower on a Walking Giant","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
← 5ddedc5 auto-data-snapshot: 2026-09-18T19:41:16 (3 data files) — dat
·
back to Model Arena
·
auto-data-snapshot: 2026-09-18T20:44:36 (3 data files) — dat 1701d74 →