← back to Model Arena
auto-data-snapshot: 2026-09-18T18:05:41 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl
86b66ca7b16228052525524ce61380579009ae65 · 2026-09-18 18:06:58 -0700 · auto-commit-fleet
Files touched
M data/challenges.jsonM yolo/arena-loop-state.jsonM yolo/daily-log.jsonl
Diff
commit 86b66ca7b16228052525524ce61380579009ae65
Author: auto-commit-fleet <steve@designerwallcoverings.com>
Date: Fri Sep 18 18:06:58 2026 -0700
auto-data-snapshot: 2026-09-18T18:05:41 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl
---
data/challenges.json | 322 +++++++++++++++++++++++++++++++++++++++++++--
yolo/arena-loop-state.json | 2 +-
yolo/daily-log.jsonl | 4 +
3 files changed, 319 insertions(+), 9 deletions(-)
diff --git a/data/challenges.json b/data/challenges.json
index d327dec..4869735 100644
--- a/data/challenges.json
+++ b/data/challenges.json
@@ -39113,7 +39113,9 @@
"finished_at": "2026-09-19T00:16:41.752Z",
"queued_at": "2026-09-19T00:16:32.292Z",
"bytes": 452,
- "thumb": true
+ "thumb": true,
+ "aiScore": null,
+ "aiReason": "judge failed: all vision panelists failed"
},
{
"model": "mac1__qwen2-5vl-7b",
@@ -39125,7 +39127,9 @@
"finished_at": "2026-09-19T00:17:19.132Z",
"queued_at": "2026-09-19T00:16:32.313Z",
"bytes": 4797,
- "thumb": true
+ "thumb": true,
+ "aiScore": null,
+ "aiReason": "judge failed: all vision panelists failed"
},
{
"model": "qwen3-14b",
@@ -39137,7 +39141,9 @@
"finished_at": "2026-09-19T00:19:52.204Z",
"queued_at": "2026-09-19T00:16:32.322Z",
"bytes": 8908,
- "thumb": true
+ "thumb": true,
+ "aiScore": null,
+ "aiReason": "judge failed: all vision panelists failed"
},
{
"model": "mlx__qwen3-next-80b-a3b-instruct-4bit",
@@ -39159,18 +39165,318 @@
"finished_at": "2026-09-19T00:20:22.633Z",
"queued_at": "2026-09-19T00:16:32.335Z",
"bytes": 4363,
- "thumb": true
+ "thumb": true,
+ "aiScore": null,
+ "aiReason": "judge failed: all vision panelists failed"
},
{
"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": "2026-09-19T00:26:32.383Z",
- "finished_at": null,
+ "finished_at": "2026-09-19T00:36:32.402Z",
"queued_at": "2026-09-19T00:16:32.341Z"
}
+ ],
+ "judging": false,
+ "aiPick": null,
+ "judged_at": "2026-09-19T00:36:32.590Z"
+ },
+ {
+ "id": "cb9b0a831fc1",
+ "title": "Culture Competition #3 — The Last Speaker",
+ "prompt": "Build this as one complete, self-contained HTML file: An interactive 'sound of a dying language' explainer for an INVENTED tongue: click words on a fading map to hear invented phonemes, watch the speaker-count clock tick down, and 'save' words into a phrasebook. 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": "Culture",
+ "designTools": false,
+ "created_at": "2026-09-19T00:41:33.411Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "mlx__qwen3-30b-a3b-instruct-2507-4bit",
+ "status": "error",
+ "error": "timeout after 600s",
+ "seconds": 600,
+ "cost": null,
+ "started_at": "2026-09-19T00:41:33.480Z",
+ "finished_at": "2026-09-19T00:51:33.501Z",
+ "queued_at": "2026-09-19T00:41:33.433Z"
+ },
+ {
+ "model": "exo__qwen3-coder-480b-a35b-instruct-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T00:41:33.485Z",
+ "finished_at": "2026-09-19T00:41:33.534Z",
+ "queued_at": "2026-09-19T00:41:33.445Z"
+ },
+ {
+ "model": "mac1__minicpm-v-latest",
+ "status": "done",
+ "error": null,
+ "seconds": 8,
+ "cost": 0,
+ "started_at": "2026-09-19T00:41:33.491Z",
+ "finished_at": "2026-09-19T00:41:41.432Z",
+ "queued_at": "2026-09-19T00:41:33.456Z",
+ "bytes": 268,
+ "thumb": true,
+ "aiScore": null,
+ "aiReason": "judge failed: all vision panelists failed"
+ },
+ {
+ "model": "exo__qwen3-5-122b-a10b-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T00:41:33.541Z",
+ "finished_at": "2026-09-19T00:41:33.592Z",
+ "queued_at": "2026-09-19T00:41:33.463Z"
+ },
+ {
+ "model": "mac1__qwen2-5vl-7b",
+ "status": "done",
+ "error": null,
+ "seconds": 27,
+ "cost": 0,
+ "started_at": "2026-09-19T00:41:41.450Z",
+ "finished_at": "2026-09-19T00:42:08.748Z",
+ "queued_at": "2026-09-19T00:41:33.469Z",
+ "bytes": 2714,
+ "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": "2026-09-19T00:41:33.598Z",
+ "finished_at": "2026-09-19T00:41:33.657Z",
+ "queued_at": "2026-09-19T00:41:33.474Z"
+ }
+ ],
+ "judging": false,
+ "aiPick": null,
+ "judged_at": "2026-09-19T00:51:33.567Z"
+ },
+ {
+ "id": "dfefdf2b9521",
+ "title": "News Competition #3 — Absurd 24-Hour News",
+ "prompt": "Build this as one complete, self-contained HTML file: A satirical INVENTED 24-hour news channel landing where three breaking stories escalate absurdly in real time via a live ticker, a 'BREAKING' klaxon toggle, and a category filter that changes the channel's whole color mood. 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": "News",
+ "designTools": false,
+ "created_at": "2026-09-19T00:56:33.829Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "exo__qwen3-6-35b-a3b-bf16",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T00:56:33.913Z",
+ "finished_at": "2026-09-19T00:56:33.954Z",
+ "queued_at": "2026-09-19T00:56:33.854Z"
+ },
+ {
+ "model": "exo__qwen3-vl-4b-instruct-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T00:56:33.961Z",
+ "finished_at": "2026-09-19T00:56:34.056Z",
+ "queued_at": "2026-09-19T00:56:33.869Z"
+ },
+ {
+ "model": "exo__minimax-m2-7",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T00:56:34.062Z",
+ "finished_at": "2026-09-19T00:56:34.105Z",
+ "queued_at": "2026-09-19T00:56:33.882Z"
+ },
+ {
+ "model": "exo__llama-3-3-70b-instruct-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T00:56:34.110Z",
+ "finished_at": "2026-09-19T00:56:34.160Z",
+ "queued_at": "2026-09-19T00:56:33.891Z"
+ },
+ {
+ "model": "exo__gemma-4-e2b-it-bf16",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T00:56:34.166Z",
+ "finished_at": "2026-09-19T00:56:34.202Z",
+ "queued_at": "2026-09-19T00:56:33.899Z"
+ },
+ {
+ "model": "exo__qwen3-next-80b-a3b-instruct-8bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T00:56:34.210Z",
+ "finished_at": "2026-09-19T00:56:34.241Z",
+ "queued_at": "2026-09-19T00:56:33.907Z"
+ }
+ ]
+ },
+ {
+ "id": "3dd7e0e71421",
+ "title": "Political Cartoon Competition #3 — Ship of State by Committee",
+ "prompt": "Build this as one complete, self-contained HTML file: A single bold SVG metaphor illustration for an INVENTED political theme — 'the ship of state steered by committee' — where dragging elements changes the metaphor's meaning and the caption adapts. Light/dark toggle. 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": "2026-09-19T01:01:42.027Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "exo__qwen3-6-27b-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T01:01:42.103Z",
+ "finished_at": "2026-09-19T01:01:42.276Z",
+ "queued_at": "2026-09-19T01:01:42.054Z"
+ },
+ {
+ "model": "exo__glm-4-7-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T01:01:42.292Z",
+ "finished_at": "2026-09-19T01:01:42.417Z",
+ "queued_at": "2026-09-19T01:01:42.067Z"
+ },
+ {
+ "model": "exo__gemma-4-31b-it-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T01:01:42.430Z",
+ "finished_at": "2026-09-19T01:01:42.575Z",
+ "queued_at": "2026-09-19T01:01:42.075Z"
+ },
+ {
+ "model": "exo__nvidia-nemotron-3-nano-30b-a3b-mlx-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T01:01:42.587Z",
+ "finished_at": "2026-09-19T01:01:42.726Z",
+ "queued_at": "2026-09-19T01:01:42.081Z"
+ },
+ {
+ "model": "exo__llama-3-1-nemotron-nano-4b-v1-1-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T01:01:42.743Z",
+ "finished_at": "2026-09-19T01:01:42.913Z",
+ "queued_at": "2026-09-19T01:01:42.089Z"
+ },
+ {
+ "model": "exo__qwen3-coder-next-6bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T01:01:42.938Z",
+ "finished_at": "2026-09-19T01:01:43.141Z",
+ "queued_at": "2026-09-19T01:01:42.096Z"
+ }
+ ]
+ },
+ {
+ "id": "358fbc67a2a5",
+ "title": "Games Competition #2 — Wake the Dragon Breakout",
+ "prompt": "Build this as one complete, self-contained HTML file: Brick-breaker where the bricks are a sleeping dragon's scales — knock them loose and the dragon slowly wakes (eyes open, breathing quickens). The paddle is a shield; a caught power-up briefly lets you paint new bricks. 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": "2026-09-19T01:06:50.406Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "exo__step-3-5-flash-6bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T01:06:50.480Z",
+ "finished_at": "2026-09-19T01:06:50.504Z",
+ "queued_at": "2026-09-19T01:06:50.425Z"
+ },
+ {
+ "model": "exo__qwen3-next-80b-a3b-thinking-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T01:06:50.510Z",
+ "finished_at": "2026-09-19T01:06:50.524Z",
+ "queued_at": "2026-09-19T01:06:50.446Z"
+ },
+ {
+ "model": "exo__deepseek-v3-1-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T01:06:50.530Z",
+ "finished_at": "2026-09-19T01:06:50.544Z",
+ "queued_at": "2026-09-19T01:06:50.456Z"
+ },
+ {
+ "model": "exo__llama-3-1-nemotron-70b-instruct-hf-8bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T01:06:50.550Z",
+ "finished_at": "2026-09-19T01:06:50.563Z",
+ "queued_at": "2026-09-19T01:06:50.462Z"
+ },
+ {
+ "model": "exo__gemma-4-e4b-it-6bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T01:06:50.569Z",
+ "finished_at": "2026-09-19T01:06:50.586Z",
+ "queued_at": "2026-09-19T01:06:50.468Z"
+ },
+ {
+ "model": "exo__nvidia-nemotron-3-nano-30b-a3b-mlx-5bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-19T01:06:50.593Z",
+ "finished_at": "2026-09-19T01:06:50.605Z",
+ "queued_at": "2026-09-19T01:06:50.474Z"
+ }
]
}
]
\ No newline at end of file
diff --git a/yolo/arena-loop-state.json b/yolo/arena-loop-state.json
index 2d85ae2..48b36d1 100644
--- a/yolo/arena-loop-state.json
+++ b/yolo/arena-loop-state.json
@@ -1 +1 @@
-{"promptIdx":3,"modelOffset":4,"compCount":{"Art":4,"Culture":2,"News":2,"Political Cartoon":2,"Games":1,"Real Work":1,"Data Viz":1,"Science":1,"Music":1,"Sports":1,"History":1,"Nature & Space":1,"Comedy":1,"Demoscene":1,"Finance":1,"Design":1},"catIdx":1,"perCat":{"Art":3,"Culture":2,"News":2,"Political Cartoon":2,"Games":1,"Real Work":1,"Data Viz":1,"Science":1,"Music":1,"Sports":1,"History":1,"Nature & Space":1,"Comedy":1,"Demoscene":1,"Finance":1,"Design":1}}
\ No newline at end of file
+{"promptIdx":3,"modelOffset":28,"compCount":{"Art":4,"Culture":3,"News":3,"Political Cartoon":3,"Games":2,"Real Work":1,"Data Viz":1,"Science":1,"Music":1,"Sports":1,"History":1,"Nature & Space":1,"Comedy":1,"Demoscene":1,"Finance":1,"Design":1},"catIdx":5,"perCat":{"Art":3,"Culture":3,"News":3,"Political Cartoon":3,"Games":2,"Real Work":1,"Data Viz":1,"Science":1,"Music":1,"Sports":1,"History":1,"Nature & Space":1,"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 7e8072f..87a75dc 100644
--- a/yolo/daily-log.jsonl
+++ b/yolo/daily-log.jsonl
@@ -74,3 +74,7 @@
{"ts":"2026-09-19T00:01:09.611Z","id":"fa151e563793","promptId":"culture-map","category":"Culture","title":"Culture Competition #2 — Festivals of Nowhere","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
{"ts":"2026-09-19T00:06:17.861Z","id":"0bc3ff42065b","promptId":"econ-brief","category":"News","title":"News Competition #2 — Teletext Econ Briefing","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
{"ts":"2026-09-19T00:11:26.267Z","id":"f61c3e8d9dd4","promptId":"satire-strip","category":"Political Cartoon","title":"Political Cartoon Competition #2 — The Form to Request a Form","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-19T00:36:32.893Z","id":"89f6f17811c2","promptId":"kinetic-type","category":"Art","title":"Art Competition #4 — Swarm Typography Poster","models":6,"done":4,"errored":2,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-19T00:51:33.745Z","id":"cb9b0a831fc1","promptId":"languages","category":"Culture","title":"Culture Competition #3 — The Last Speaker","models":6,"done":2,"errored":4,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-19T00:56:41.918Z","id":"dfefdf2b9521","promptId":"news-ticker","category":"News","title":"News Competition #3 — Absurd 24-Hour News","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-19T01:01:50.108Z","id":"3dd7e0e71421","promptId":"metaphor","category":"Political Cartoon","title":"Political Cartoon Competition #3 — Ship of State by Committee","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
← 3feaf18 auto-data-snapshot: 2026-09-18T17:33:52 (3 data files) — dat
·
back to Model Arena
·
auto-data-snapshot: 2026-09-18T18:37:36 (3 data files) — dat 1af9185 →