[object Object]

← back to Model Arena

auto-data-snapshot: 2026-09-26T19:53:16 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl

d232fb004c43c8e292c9800a93bdf5b4f1426490 · 2026-09-26 19:53:41 -0700 · auto-commit-fleet

Files touched

Diff

commit d232fb004c43c8e292c9800a93bdf5b4f1426490
Author: auto-commit-fleet <steve@designerwallcoverings.com>
Date:   Sat Sep 26 19:53:41 2026 -0700

    auto-data-snapshot: 2026-09-26T19:53:16 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl
---
 data/challenges.json       | 172 ++++++++++++++++++++++++++++++++++++++++++++-
 yolo/arena-loop-state.json |   2 +-
 yolo/daily-log.jsonl       |   2 +
 3 files changed, 172 insertions(+), 4 deletions(-)

diff --git a/data/challenges.json b/data/challenges.json
index 7fa63df..d71594c 100644
--- a/data/challenges.json
+++ b/data/challenges.json
@@ -95753,7 +95753,9 @@
         "finished_at": "2026-09-27T02:14:36.181Z",
         "queued_at": "2026-09-27T02:10:24.173Z",
         "bytes": 14077,
-        "thumb": true
+        "thumb": true,
+        "aiScore": null,
+        "aiReason": "judge failed: all vision panelists failed"
       },
       {
         "model": "mlx__qwen3-8-27b-8bit",
@@ -95768,14 +95770,178 @@
       },
       {
         "model": "exo__minimax-m2-7-4bit",
+        "status": "error",
+        "error": "timeout after 300s",
+        "seconds": 300,
+        "cost": null,
+        "started_at": "2026-09-27T02:20:25.671Z",
+        "finished_at": "2026-09-27T02:25:25.879Z",
+        "queued_at": "2026-09-27T02:10:24.439Z",
+        "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)"
+      }
+    ],
+    "judging": false,
+    "aiPick": null,
+    "judged_at": "2026-09-27T02:25:26.027Z"
+  },
+  {
+    "id": "8b75f3d3f58b",
+    "title": "Comedy Competition #39 — Roast or Toast Campfire",
+    "prompt": "Build this as one complete, self-contained HTML file: A good-natured 'Roast or Toast' campfire where a toggle sends compliments or playful roasts at escalating heat levels shown as literal flames, with shareable text and a 'mercy' button. Keep it kind. 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": "Comedy",
+    "designTools": false,
+    "created_at": "2026-09-27T02:30:29.876Z",
+    "winner": null,
+    "runs": [
+      {
+        "model": "qwen25-7b",
+        "status": "done",
+        "error": null,
+        "seconds": 29,
+        "cost": 0,
+        "started_at": "2026-09-27T02:30:30.324Z",
+        "finished_at": "2026-09-27T02:30:59.528Z",
+        "queued_at": "2026-09-27T02:30:29.954Z",
+        "bytes": 3773,
+        "thumb": true,
+        "aiScore": null,
+        "aiReason": "judge failed: all vision panelists failed"
+      },
+      {
+        "model": "mlx__qwen3-30b-a3b-instruct-2507-4bit",
+        "status": "error",
+        "error": "openai-local bad response: 404",
+        "seconds": 300,
+        "cost": null,
+        "started_at": "2026-09-27T02:30:30.392Z",
+        "finished_at": "2026-09-27T02:35:30.884Z",
+        "queued_at": "2026-09-27T02:30:30.034Z",
+        "fellBack": "http://127.0.0.1:52415 (mlx-community/MiniMax-M2.7-4bit)"
+      },
+      {
+        "model": "exo__qwen3-coder-480b-a35b-instruct-4bit",
+        "status": "error",
+        "error": "timeout after 300s",
+        "seconds": 300,
+        "cost": null,
+        "started_at": "2026-09-27T02:30:30.452Z",
+        "finished_at": "2026-09-27T02:35:30.721Z",
+        "queued_at": "2026-09-27T02:30:30.092Z",
+        "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)"
+      },
+      {
+        "model": "mac1__minicpm-v-latest",
+        "status": "done",
+        "error": null,
+        "seconds": 22,
+        "cost": 0,
+        "started_at": "2026-09-27T02:30:59.567Z",
+        "finished_at": "2026-09-27T02:31:21.951Z",
+        "queued_at": "2026-09-27T02:30:30.156Z",
+        "bytes": 2721,
+        "thumb": true,
+        "aiScore": null,
+        "aiReason": "judge failed: all vision panelists failed"
+      },
+      {
+        "model": "mlx__qwen3-next-80b-a3b-instruct-4bit",
+        "status": "error",
+        "error": "openai-local bad response: 404",
+        "seconds": 301,
+        "cost": null,
+        "started_at": "2026-09-27T02:35:31.021Z",
+        "finished_at": "2026-09-27T02:40:31.681Z",
+        "queued_at": "2026-09-27T02:30:30.217Z",
+        "fellBack": "http://127.0.0.1:52415 (mlx-community/Qwen3-Next-80B-A3B-Instruct-4bit)"
+      },
+      {
+        "model": "exo__qwen3-5-122b-a10b-4bit",
+        "status": "error",
+        "error": "timeout after 300s",
+        "seconds": 301,
+        "cost": null,
+        "started_at": "2026-09-27T02:35:30.773Z",
+        "finished_at": "2026-09-27T02:40:31.428Z",
+        "queued_at": "2026-09-27T02:30:30.271Z",
+        "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)"
+      }
+    ],
+    "judging": false,
+    "aiPick": null,
+    "judged_at": "2026-09-27T02:40:32.372Z"
+  },
+  {
+    "id": "9b6328c83d91",
+    "title": "Demoscene Competition #39 — Slime Creature Terrarium",
+    "prompt": "Build this as one complete, self-contained HTML file: Gooey metaballs staged as a terrarium of glowing 'slime creatures' that merge and split; controls for count/threshold/palette, a cursor that repels them, and a snapshot button. 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": "Demoscene",
+    "designTools": false,
+    "created_at": "2026-09-27T02:45:39.150Z",
+    "winner": null,
+    "runs": [
+      {
+        "model": "mac1__qwen2-5vl-7b",
+        "status": "done",
+        "error": null,
+        "seconds": 45,
+        "cost": 0,
+        "started_at": "2026-09-27T02:45:39.813Z",
+        "finished_at": "2026-09-27T02:46:25.220Z",
+        "queued_at": "2026-09-27T02:45:39.363Z",
+        "bytes": 5010,
+        "thumb": true
+      },
+      {
+        "model": "mlx__mlx-community-qwen3-30b-a3b-instruct-2507-4bit",
+        "status": "error",
+        "error": "timeout after 300s",
+        "seconds": 300,
+        "cost": null,
+        "started_at": "2026-09-27T02:45:39.978Z",
+        "finished_at": "2026-09-27T02:50:40.377Z",
+        "queued_at": "2026-09-27T02:45:39.500Z"
+      },
+      {
+        "model": "exo__gemma-4-26b-a4b-it-6bit",
+        "status": "error",
+        "error": "timeout after 300s",
+        "seconds": 300,
+        "cost": null,
+        "started_at": "2026-09-27T02:45:40.165Z",
+        "finished_at": "2026-09-27T02:50:40.767Z",
+        "queued_at": "2026-09-27T02:45:39.566Z",
+        "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)"
+      },
+      {
+        "model": "exo__qwen3-6-35b-a3b-bf16",
         "status": "running",
         "error": null,
         "seconds": null,
         "cost": null,
-        "started_at": "2026-09-27T02:20:25.671Z",
+        "started_at": "2026-09-27T02:50:40.799Z",
         "finished_at": null,
-        "queued_at": "2026-09-27T02:10:24.439Z",
+        "queued_at": "2026-09-27T02:45:39.624Z",
         "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)"
+      },
+      {
+        "model": "exo__qwen3-vl-4b-instruct-4bit",
+        "status": "queued",
+        "error": null,
+        "seconds": null,
+        "cost": null,
+        "started_at": null,
+        "finished_at": null,
+        "queued_at": "2026-09-27T02:45:39.684Z"
+      },
+      {
+        "model": "exo__minimax-m2-7",
+        "status": "queued",
+        "error": null,
+        "seconds": null,
+        "cost": null,
+        "started_at": null,
+        "finished_at": null,
+        "queued_at": "2026-09-27T02:45:39.732Z"
       }
     ]
   }
diff --git a/yolo/arena-loop-state.json b/yolo/arena-loop-state.json
index 1fecb13..a0187ed 100644
--- a/yolo/arena-loop-state.json
+++ b/yolo/arena-loop-state.json
@@ -1 +1 @@
-{"promptIdx":3,"modelOffset":3,"compCount":{"Art":78,"Culture":77,"News":77,"Political Cartoon":77,"Games":39,"Real Work":39,"Data Viz":39,"Science":39,"Music":39,"Sports":39,"History":39,"Nature & Space":39,"Comedy":38,"Demoscene":38,"Finance":38,"Design":38},"catIdx":12,"perCat":{"Art":1,"Culture":1,"News":1,"Political Cartoon":1,"Games":3,"Real Work":3,"Data Viz":3,"Science":3,"Music":3,"Sports":3,"History":3,"Nature & Space":3,"Comedy":2,"Demoscene":2,"Finance":2,"Design":2}}
\ No newline at end of file
+{"promptIdx":3,"modelOffset":15,"compCount":{"Art":78,"Culture":77,"News":77,"Political Cartoon":77,"Games":39,"Real Work":39,"Data Viz":39,"Science":39,"Music":39,"Sports":39,"History":39,"Nature & Space":39,"Comedy":39,"Demoscene":39,"Finance":38,"Design":38},"catIdx":14,"perCat":{"Art":1,"Culture":1,"News":1,"Political Cartoon":1,"Games":3,"Real Work":3,"Data Viz":3,"Science":3,"Music":3,"Sports":3,"History":3,"Nature & Space":3,"Comedy":3,"Demoscene":3,"Finance":2,"Design":2}}
\ No newline at end of file
diff --git a/yolo/daily-log.jsonl b/yolo/daily-log.jsonl
index a673579..4fc4ee2 100644
--- a/yolo/daily-log.jsonl
+++ b/yolo/daily-log.jsonl
@@ -868,3 +868,5 @@
 {"ts":"2026-09-27T00:55:16.535Z","id":"62a42a0c0112","promptId":"audioviz","category":"Music","title":"Music Competition #39 — Skyline Audio Visualizer","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
 {"ts":"2026-09-27T01:30:20.051Z","id":"8fc71ff97694","promptId":"statcard","category":"Sports","title":"Sports Competition #39 — Holographic Stat Cards","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
 {"ts":"2026-09-27T02:05:23.133Z","id":"7b0f6ffc48d4","promptId":"artifact","category":"History","title":"History Competition #39 — Spotlit Relic Viewer","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-27T02:25:29.787Z","id":"b49528c34c04","promptId":"weather","category":"Nature & Space","title":"Nature & Space Competition #39 — Shake-the-Snow-Globe Weather","models":6,"done":1,"errored":5,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-27T02:40:38.982Z","id":"8b75f3d3f58b","promptId":"roast","category":"Comedy","title":"Comedy Competition #39 — Roast or Toast Campfire","models":6,"done":2,"errored":4,"settled":true,"aiPick":null,"loop":true}

← 84aa220 auto-data-snapshot: 2026-09-26T19:22:47 (3 data files) — dat  ·  back to Model Arena  ·  auto-data-snapshot: 2026-09-26T20:23:45 (3 data files) — dat 207634a →