← back to Model Arena
auto-data-snapshot: 2026-09-20T03:19:32 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl
a459371b34aca323440fc850a4e552a036324ea6 · 2026-09-20 03:21:46 -0700 · auto-commit-fleet
Files touched
M data/challenges.jsonM yolo/arena-loop-state.jsonM yolo/daily-log.jsonl
Diff
commit a459371b34aca323440fc850a4e552a036324ea6
Author: auto-commit-fleet <steve@designerwallcoverings.com>
Date: Sun Sep 20 03:21:46 2026 -0700
auto-data-snapshot: 2026-09-20T03:19:32 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl
---
data/challenges.json | 292 ++++++++++++++++++++++++++++++++++++++++++++-
yolo/arena-loop-state.json | 2 +-
yolo/daily-log.jsonl | 5 +
3 files changed, 294 insertions(+), 5 deletions(-)
diff --git a/data/challenges.json b/data/challenges.json
index 677cf52..e0d4f79 100644
--- a/data/challenges.json
+++ b/data/challenges.json
@@ -62318,12 +62318,12 @@
},
{
"model": "mlx__qwen3-next-80b-a3b-instruct-4bit",
- "status": "running",
- "error": null,
- "seconds": null,
+ "status": "error",
+ "error": "timeout after 600s",
+ "seconds": 600,
"cost": null,
"started_at": "2026-09-20T09:46:50.354Z",
- "finished_at": null,
+ "finished_at": "2026-09-20T09:56:50.408Z",
"queued_at": "2026-09-20T09:36:50.121Z"
},
{
@@ -62347,5 +62347,289 @@
"queued_at": "2026-09-20T09:36:50.219Z"
}
]
+ },
+ {
+ "id": "a6d866621482",
+ "title": "Games Competition #18 — 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": "2026-09-20T10:01:50.816Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "exo__qwen3-5-122b-a10b-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T10:01:50.970Z",
+ "finished_at": "2026-09-20T10:01:51.014Z",
+ "queued_at": "2026-09-20T10:01:50.840Z"
+ },
+ {
+ "model": "mac1__qwen2-5vl-7b",
+ "status": "error",
+ "error": "ollama bad response: 503",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T10:01:50.988Z",
+ "finished_at": "2026-09-20T10:01:51.209Z",
+ "queued_at": "2026-09-20T10:01:50.861Z"
+ },
+ {
+ "model": "exo__gemma-4-26b-a4b-it-6bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T10:01:51.033Z",
+ "finished_at": "2026-09-20T10:01:51.059Z",
+ "queued_at": "2026-09-20T10:01:50.879Z"
+ },
+ {
+ "model": "exo__qwen3-6-35b-a3b-bf16",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T10:01:51.077Z",
+ "finished_at": "2026-09-20T10:01:51.103Z",
+ "queued_at": "2026-09-20T10:01:50.898Z"
+ },
+ {
+ "model": "exo__qwen3-vl-4b-instruct-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T10:01:51.122Z",
+ "finished_at": "2026-09-20T10:01:51.146Z",
+ "queued_at": "2026-09-20T10:01:50.924Z"
+ },
+ {
+ "model": "exo__minimax-m2-7",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T10:01:51.165Z",
+ "finished_at": "2026-09-20T10:01:51.190Z",
+ "queued_at": "2026-09-20T10:01:50.951Z"
+ }
+ ]
+ },
+ {
+ "id": "410104c6f277",
+ "title": "Real Work Competition #18 — Lighthouse Focus Timer",
+ "prompt": "Build this as one complete, self-contained HTML file: A focus timer styled as a tiny lighthouse: work sessions sweep the beam and calm the sea, breaks bring gentle waves, a task list is the ships to guide home, and session stats show the night's safe passages. 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": "Real Work",
+ "designTools": false,
+ "created_at": "2026-09-20T10:06:59.011Z",
+ "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": "2026-09-20T10:06:59.148Z",
+ "finished_at": "2026-09-20T10:06:59.172Z",
+ "queued_at": "2026-09-20T10:06:59.032Z"
+ },
+ {
+ "model": "exo__gemma-4-e2b-it-bf16",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T10:06:59.190Z",
+ "finished_at": "2026-09-20T10:06:59.212Z",
+ "queued_at": "2026-09-20T10:06:59.052Z"
+ },
+ {
+ "model": "exo__qwen3-next-80b-a3b-instruct-8bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T10:06:59.230Z",
+ "finished_at": "2026-09-20T10:06:59.253Z",
+ "queued_at": "2026-09-20T10:06:59.072Z"
+ },
+ {
+ "model": "exo__qwen3-6-27b-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T10:06:59.272Z",
+ "finished_at": "2026-09-20T10:06:59.294Z",
+ "queued_at": "2026-09-20T10:06:59.091Z"
+ },
+ {
+ "model": "exo__glm-4-7-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T10:06:59.313Z",
+ "finished_at": "2026-09-20T10:06:59.336Z",
+ "queued_at": "2026-09-20T10:06:59.111Z"
+ },
+ {
+ "model": "exo__gemma-4-31b-it-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T10:06:59.356Z",
+ "finished_at": "2026-09-20T10:06:59.377Z",
+ "queued_at": "2026-09-20T10:06:59.128Z"
+ }
+ ]
+ },
+ {
+ "id": "6f3c8d92e3b1",
+ "title": "Data Viz Competition #18 — Planet Dating Show",
+ "prompt": "Build this as one complete, self-contained HTML file: A scatter-plot 'dating show' for INVENTED planets: each dot is a world, axis pickers change what makes a 'good match', lasso-select to form a shortlist, and a summary narrates the cluster you drew. 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": "Data Viz",
+ "designTools": false,
+ "created_at": "2026-09-20T10:12:07.175Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "exo__nvidia-nemotron-3-nano-30b-a3b-mlx-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T10:12:07.314Z",
+ "finished_at": "2026-09-20T10:12:07.337Z",
+ "queued_at": "2026-09-20T10:12:07.196Z"
+ },
+ {
+ "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": "2026-09-20T10:12:07.356Z",
+ "finished_at": "2026-09-20T10:12:07.379Z",
+ "queued_at": "2026-09-20T10:12:07.216Z"
+ },
+ {
+ "model": "exo__qwen3-coder-next-6bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T10:12:07.397Z",
+ "finished_at": "2026-09-20T10:12:07.419Z",
+ "queued_at": "2026-09-20T10:12:07.239Z"
+ },
+ {
+ "model": "exo__step-3-5-flash-6bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T10:12:07.439Z",
+ "finished_at": "2026-09-20T10:12:07.463Z",
+ "queued_at": "2026-09-20T10:12:07.258Z"
+ },
+ {
+ "model": "exo__qwen3-next-80b-a3b-thinking-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T10:12:07.494Z",
+ "finished_at": "2026-09-20T10:12:07.537Z",
+ "queued_at": "2026-09-20T10:12:07.276Z"
+ },
+ {
+ "model": "exo__deepseek-v3-1-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T10:12:07.555Z",
+ "finished_at": "2026-09-20T10:12:07.577Z",
+ "queued_at": "2026-09-20T10:12:07.295Z"
+ }
+ ]
+ },
+ {
+ "id": "00a4468cc5bc",
+ "title": "Science Competition #18 — Cell as a Factory-City",
+ "prompt": "Build this as one complete, self-contained HTML file: A cell explainer as a bustling factory-city (SVG): click organelles to read their 'job posting' and watch a glucose delivery truck route through the city to make ATP, with a guided tour and a quiz-yourself mode. 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": "Science",
+ "designTools": false,
+ "created_at": "2026-09-20T10:17:15.349Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "exo__llama-3-1-nemotron-70b-instruct-hf-8bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T10:17:15.556Z",
+ "finished_at": "2026-09-20T10:17:15.580Z",
+ "queued_at": "2026-09-20T10:17:15.382Z"
+ },
+ {
+ "model": "exo__gemma-4-e4b-it-6bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T10:17:15.601Z",
+ "finished_at": "2026-09-20T10:17:15.624Z",
+ "queued_at": "2026-09-20T10:17:15.410Z"
+ },
+ {
+ "model": "exo__nvidia-nemotron-3-nano-30b-a3b-mlx-5bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T10:17:15.643Z",
+ "finished_at": "2026-09-20T10:17:15.667Z",
+ "queued_at": "2026-09-20T10:17:15.442Z"
+ },
+ {
+ "model": "exo__glm-4-7-flash-6bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T10:17:15.685Z",
+ "finished_at": "2026-09-20T10:17:15.708Z",
+ "queued_at": "2026-09-20T10:17:15.468Z"
+ },
+ {
+ "model": "exo__qwen3-5-35b-a3b-8bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T10:17:15.726Z",
+ "finished_at": "2026-09-20T10:17:15.749Z",
+ "queued_at": "2026-09-20T10:17:15.504Z"
+ },
+ {
+ "model": "exo__glm-4-7-8bit-gs32",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T10:17:15.772Z",
+ "finished_at": "2026-09-20T10:17:15.796Z",
+ "queued_at": "2026-09-20T10:17:15.534Z"
+ }
+ ]
}
]
\ No newline at end of file
diff --git a/yolo/arena-loop-state.json b/yolo/arena-loop-state.json
index 658a96f..a7c4de4 100644
--- a/yolo/arena-loop-state.json
+++ b/yolo/arena-loop-state.json
@@ -1 +1 @@
-{"promptIdx":3,"modelOffset":7,"compCount":{"Art":36,"Culture":35,"News":35,"Political Cartoon":35,"Games":17,"Real Work":17,"Data Viz":17,"Science":17,"Music":17,"Sports":17,"History":17,"Nature & Space":17,"Comedy":17,"Demoscene":17,"Finance":17,"Design":17},"catIdx":4,"perCat":{"Art":3,"Culture":3,"News":3,"Political Cartoon":3,"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":31,"compCount":{"Art":36,"Culture":35,"News":35,"Political Cartoon":35,"Games":18,"Real Work":18,"Data Viz":18,"Science":18,"Music":17,"Sports":17,"History":17,"Nature & Space":17,"Comedy":17,"Demoscene":17,"Finance":17,"Design":17},"catIdx":8,"perCat":{"Art":3,"Culture":3,"News":3,"Political Cartoon":3,"Games":3,"Real Work":3,"Data Viz":3,"Science":3,"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 52fdde4..f832095 100644
--- a/yolo/daily-log.jsonl
+++ b/yolo/daily-log.jsonl
@@ -398,3 +398,8 @@
{"ts":"2026-09-20T09:19:17.205Z","id":"128bca14bd15","promptId":"kinetic-type","category":"Art","title":"Art Competition #36 — Swarm Typography Poster","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
{"ts":"2026-09-20T09:24:25.447Z","id":"b8d3ae3791e3","promptId":"languages","category":"Culture","title":"Culture Competition #35 — The Last Speaker","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
{"ts":"2026-09-20T09:31:49.814Z","id":"b5d53c4ab9bd","promptId":"news-ticker","category":"News","title":"News Competition #35 — Absurd 24-Hour News","models":6,"done":1,"errored":5,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-20T09:56:50.780Z","id":"4884dfd03cb4","promptId":"metaphor","category":"Political Cartoon","title":"Political Cartoon Competition #35 — Ship of State by Committee","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-20T10:01:58.977Z","id":"a6d866621482","promptId":"tower","category":"Games","title":"Games Competition #18 — Tower on a Walking Giant","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-20T10:07:07.151Z","id":"410104c6f277","promptId":"pomodoro","category":"Real Work","title":"Real Work Competition #18 — Lighthouse Focus Timer","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-20T10:12:15.318Z","id":"6f3c8d92e3b1","promptId":"scatter","category":"Data Viz","title":"Data Viz Competition #18 — Planet Dating Show","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-20T10:17:23.559Z","id":"00a4468cc5bc","promptId":"cell","category":"Science","title":"Science Competition #18 — Cell as a Factory-City","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
← 48e7e47 auto-data-snapshot: 2026-09-20T02:45:46 (3 data files) — dat
·
back to Model Arena
·
auto-data-snapshot: 2026-09-20T03:53:01 (3 data files) — dat 1dbbe1c →