← back to Model Arena
auto-data-snapshot: 2026-09-20T13:56:34 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl
819947073666c97b072944f63c961b899343b799 · 2026-09-20 13:58:26 -0700 · auto-commit-fleet
Files touched
M data/challenges.jsonM yolo/arena-loop-state.jsonM yolo/daily-log.jsonl
Diff
commit 819947073666c97b072944f63c961b899343b799
Author: auto-commit-fleet <steve@designerwallcoverings.com>
Date: Sun Sep 20 13:58:26 2026 -0700
auto-data-snapshot: 2026-09-20T13:56:34 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl
---
data/challenges.json | 220 +++++++++++++++++++++++++++++++++++++++++++++
yolo/arena-loop-state.json | 2 +-
yolo/daily-log.jsonl | 3 +
3 files changed, 224 insertions(+), 1 deletion(-)
diff --git a/data/challenges.json b/data/challenges.json
index d60770d..0874394 100644
--- a/data/challenges.json
+++ b/data/challenges.json
@@ -69868,5 +69868,225 @@
"queued_at": "2026-09-20T20:22:08.416Z"
}
]
+ },
+ {
+ "id": "a94eb83ee96f",
+ "title": "Sports Competition #23 — Mascot Clash Bracket",
+ "prompt": "Build this as one complete, self-contained HTML file: A single-elim bracket for INVENTED mascots where clicking a winner triggers a 2-second SVG 'clash' animation before advancing, with seeding, highlighted upsets, and a champion confetti reveal. 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": "Sports",
+ "designTools": false,
+ "created_at": "2026-09-20T20:27:16.574Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "exo__deepseek-v4-pro",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T20:27:16.872Z",
+ "finished_at": "2026-09-20T20:27:16.902Z",
+ "queued_at": "2026-09-20T20:27:16.620Z"
+ },
+ {
+ "model": "exo__deepseek-v3-1-8bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T20:27:16.925Z",
+ "finished_at": "2026-09-20T20:27:16.957Z",
+ "queued_at": "2026-09-20T20:27:16.657Z"
+ },
+ {
+ "model": "exo__glm-5-8bit-mxfp8",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T20:27:16.983Z",
+ "finished_at": "2026-09-20T20:27:17.011Z",
+ "queued_at": "2026-09-20T20:27:16.729Z"
+ },
+ {
+ "model": "exo__nvidia-nemotron-3-nano-30b-a3b-mlx-mxfp4",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T20:27:17.039Z",
+ "finished_at": "2026-09-20T20:27:17.076Z",
+ "queued_at": "2026-09-20T20:27:16.766Z"
+ },
+ {
+ "model": "exo__llama-3-1-nemotron-nano-4b-v1-1-8bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T20:27:17.101Z",
+ "finished_at": "2026-09-20T20:27:17.140Z",
+ "queued_at": "2026-09-20T20:27:16.796Z"
+ },
+ {
+ "model": "exo__kimi-k2-6",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T20:27:17.168Z",
+ "finished_at": "2026-09-20T20:27:17.199Z",
+ "queued_at": "2026-09-20T20:27:16.849Z"
+ }
+ ]
+ },
+ {
+ "id": "1a357c868e55",
+ "title": "History Competition #23 — An Empire That Breathes",
+ "prompt": "Build this as one complete, self-contained HTML file: An INVENTED empire that breathes across a map as you drag a century slider — borders bloom and recede, cities rise as glowing dots, and event notes fade in at the turning points, with a legend. 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": "2026-09-20T20:32:24.929Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "exo__nvidia-nemotron-3-nano-30b-a3b-mlx-8bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T20:32:25.193Z",
+ "finished_at": "2026-09-20T20:32:25.292Z",
+ "queued_at": "2026-09-20T20:32:24.969Z"
+ },
+ {
+ "model": "exo__gemma-4-31b-it-8bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T20:32:25.314Z",
+ "finished_at": "2026-09-20T20:32:25.346Z",
+ "queued_at": "2026-09-20T20:32:25.013Z"
+ },
+ {
+ "model": "qwen3-14b",
+ "status": "done",
+ "error": null,
+ "seconds": 134,
+ "cost": 0,
+ "started_at": "2026-09-20T20:32:25.230Z",
+ "finished_at": "2026-09-20T20:34:39.666Z",
+ "queued_at": "2026-09-20T20:32:25.055Z",
+ "bytes": 8172,
+ "thumb": true,
+ "aiScore": null,
+ "aiReason": "judge failed: all vision panelists failed"
+ },
+ {
+ "model": "mlx__qwen3-30b-a3b-instruct-2507-4bit",
+ "status": "error",
+ "error": "timeout after 600s",
+ "seconds": 600,
+ "cost": null,
+ "started_at": "2026-09-20T20:32:25.264Z",
+ "finished_at": "2026-09-20T20:42:25.294Z",
+ "queued_at": "2026-09-20T20:32:25.097Z"
+ },
+ {
+ "model": "exo__minimax-m2-7-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T20:32:25.370Z",
+ "finished_at": "2026-09-20T20:32:25.397Z",
+ "queued_at": "2026-09-20T20:32:25.138Z"
+ },
+ {
+ "model": "qwen25-7b",
+ "status": "error",
+ "error": "ollama bad response: 503",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T20:34:39.696Z",
+ "finished_at": "2026-09-20T20:34:39.881Z",
+ "queued_at": "2026-09-20T20:32:25.168Z"
+ }
+ ],
+ "judging": false,
+ "aiPick": null,
+ "judged_at": "2026-09-20T20:42:25.545Z"
+ },
+ {
+ "id": "2bf03c9598b3",
+ "title": "Nature & Space Competition #23 — 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": "2026-09-20T20:47:25.496Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "mlx__qwen3-next-80b-a3b-instruct-4bit",
+ "status": "error",
+ "error": "timeout after 600s",
+ "seconds": 600,
+ "cost": null,
+ "started_at": "2026-09-20T20:47:25.715Z",
+ "finished_at": "2026-09-20T20:57:25.776Z",
+ "queued_at": "2026-09-20T20:47:25.537Z"
+ },
+ {
+ "model": "exo__qwen3-coder-480b-a35b-instruct-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T20:47:25.738Z",
+ "finished_at": "2026-09-20T20:47:25.827Z",
+ "queued_at": "2026-09-20T20:47:25.578Z"
+ },
+ {
+ "model": "mac1__minicpm-v-latest",
+ "status": "error",
+ "error": "ollama bad response: 503",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T20:47:25.783Z",
+ "finished_at": "2026-09-20T20:47:25.982Z",
+ "queued_at": "2026-09-20T20:47:25.603Z"
+ },
+ {
+ "model": "exo__qwen3-5-122b-a10b-4bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T20:47:25.849Z",
+ "finished_at": "2026-09-20T20:47:25.879Z",
+ "queued_at": "2026-09-20T20:47:25.626Z"
+ },
+ {
+ "model": "mac1__qwen2-5vl-7b",
+ "status": "error",
+ "error": "ollama bad response: 503",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T20:47:26.017Z",
+ "finished_at": "2026-09-20T20:47:26.205Z",
+ "queued_at": "2026-09-20T20:47:25.659Z"
+ },
+ {
+ "model": "exo__gemma-4-26b-a4b-it-6bit",
+ "status": "error",
+ "error": "openai-local bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-20T20:47:25.904Z",
+ "finished_at": "2026-09-20T20:47:25.934Z",
+ "queued_at": "2026-09-20T20:47:25.690Z"
+ }
+ ]
}
]
\ No newline at end of file
diff --git a/yolo/arena-loop-state.json b/yolo/arena-loop-state.json
index 04f055e..5827899 100644
--- a/yolo/arena-loop-state.json
+++ b/yolo/arena-loop-state.json
@@ -1 +1 @@
-{"promptIdx":3,"modelOffset":121,"compCount":{"Art":46,"Culture":45,"News":45,"Political Cartoon":45,"Games":23,"Real Work":23,"Data Viz":23,"Science":23,"Music":23,"Sports":22,"History":22,"Nature & Space":22,"Comedy":22,"Demoscene":22,"Finance":22,"Design":22},"catIdx":9,"perCat":{"Art":1,"Culture":1,"News":1,"Political Cartoon":1,"Games":2,"Real Work":2,"Data Viz":2,"Science":2,"Music":2,"Sports":1,"History":1,"Nature & Space":1,"Comedy":1,"Demoscene":1,"Finance":1,"Design":1}}
\ No newline at end of file
+{"promptIdx":3,"modelOffset":10,"compCount":{"Art":46,"Culture":45,"News":45,"Political Cartoon":45,"Games":23,"Real Work":23,"Data Viz":23,"Science":23,"Music":23,"Sports":23,"History":23,"Nature & Space":23,"Comedy":22,"Demoscene":22,"Finance":22,"Design":22},"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 07712a6..2ea1838 100644
--- a/yolo/daily-log.jsonl
+++ b/yolo/daily-log.jsonl
@@ -505,3 +505,6 @@
{"ts":"2026-09-20T20:11:59.655Z","id":"d400c3b6fb9b","promptId":"flow-infographic","category":"Data Viz","title":"Data Viz Competition #23 — Bean-to-Cup Sankey","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
{"ts":"2026-09-20T20:17:07.907Z","id":"e99c46b33fcd","promptId":"pendulum","category":"Science","title":"Science Competition #23 — The Painting Pendulum","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
{"ts":"2026-09-20T20:22:16.459Z","id":"34990b396e5f","promptId":"synth","category":"Music","title":"Music Competition #23 — The Singing Creature Synth","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-20T20:27:24.879Z","id":"a94eb83ee96f","promptId":"bracket","category":"Sports","title":"Sports Competition #23 — Mascot Clash Bracket","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-20T20:42:25.459Z","id":"1a357c868e55","promptId":"empire-map","category":"History","title":"History Competition #23 — An Empire That Breathes","models":6,"done":1,"errored":5,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-20T20:57:26.001Z","id":"2bf03c9598b3","promptId":"ecosystem","category":"Nature & Space","title":"Nature & Space Competition #23 — Terrarium in a Jar","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
← 1f0c22e auto-data-snapshot: 2026-09-20T13:23:13 (3 data files) — dat
·
back to Model Arena
·
auto-data-snapshot: 2026-09-20T14:29:43 (3 data files) — dat 9f8c191 →