[object Object]

← back to Model Arena

auto-data-snapshot: 2026-09-19T09:27:32 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl

66eefaa238c20ae34a21688942577f72869e7961 · 2026-09-19 09:28:41 -0700 · auto-commit-fleet

Files touched

Diff

commit 66eefaa238c20ae34a21688942577f72869e7961
Author: auto-commit-fleet <steve@designerwallcoverings.com>
Date:   Sat Sep 19 09:28:41 2026 -0700

    auto-data-snapshot: 2026-09-19T09:27:32 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl
---
 data/challenges.json       | 149 +++++++++++++++++++++++++++++++++++++++++++++
 yolo/arena-loop-state.json |   2 +-
 yolo/daily-log.jsonl       |   2 +
 3 files changed, 152 insertions(+), 1 deletion(-)

diff --git a/data/challenges.json b/data/challenges.json
index 6ac6eff..1ce40e9 100644
--- a/data/challenges.json
+++ b/data/challenges.json
@@ -49937,5 +49937,154 @@
         "queued_at": "2026-09-19T15:53:19.583Z"
       }
     ]
+  },
+  {
+    "id": "8255d17be8ed",
+    "title": "History Competition #9 — Spotlit Relic Viewer",
+    "prompt": "Build this as one complete, self-contained HTML file: A museum artifact viewer where an INVENTED relic rotates as a chunky CSS-3D object under a movable spotlight; click facets to reveal provenance and era context, with next/prev and a 'restore vs weathered' 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": "History",
+    "designTools": false,
+    "created_at": "2026-09-19T15:58:27.646Z",
+    "winner": null,
+    "runs": [
+      {
+        "model": "exo__nvidia-nemotron-3-nano-30b-a3b-mlx-mxfp4",
+        "status": "error",
+        "error": "openai-local bad response: 404",
+        "seconds": 0,
+        "cost": null,
+        "started_at": "2026-09-19T15:58:27.753Z",
+        "finished_at": "2026-09-19T15:58:27.787Z",
+        "queued_at": "2026-09-19T15:58:27.664Z"
+      },
+      {
+        "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": "2026-09-19T15:58:27.802Z",
+        "finished_at": "2026-09-19T15:58:27.824Z",
+        "queued_at": "2026-09-19T15:58:27.680Z"
+      },
+      {
+        "model": "exo__kimi-k2-6",
+        "status": "error",
+        "error": "openai-local bad response: 404",
+        "seconds": 0,
+        "cost": null,
+        "started_at": "2026-09-19T15:58:27.845Z",
+        "finished_at": "2026-09-19T15:58:27.879Z",
+        "queued_at": "2026-09-19T15:58:27.695Z"
+      },
+      {
+        "model": "exo__nvidia-nemotron-3-nano-30b-a3b-mlx-8bit",
+        "status": "error",
+        "error": "openai-local bad response: 404",
+        "seconds": 0,
+        "cost": null,
+        "started_at": "2026-09-19T15:58:27.894Z",
+        "finished_at": "2026-09-19T15:58:27.915Z",
+        "queued_at": "2026-09-19T15:58:27.710Z"
+      },
+      {
+        "model": "exo__gemma-4-31b-it-8bit",
+        "status": "error",
+        "error": "openai-local bad response: 404",
+        "seconds": 0,
+        "cost": null,
+        "started_at": "2026-09-19T15:58:27.930Z",
+        "finished_at": "2026-09-19T15:58:27.949Z",
+        "queued_at": "2026-09-19T15:58:27.725Z"
+      },
+      {
+        "model": "qwen3-14b",
+        "status": "done",
+        "error": null,
+        "seconds": 181,
+        "cost": 0,
+        "started_at": "2026-09-19T15:58:27.768Z",
+        "finished_at": "2026-09-19T16:01:28.344Z",
+        "queued_at": "2026-09-19T15:58:27.739Z",
+        "bytes": 11899,
+        "thumb": true,
+        "aiScore": null,
+        "aiReason": "judge failed: all vision panelists failed"
+      }
+    ],
+    "judging": false,
+    "aiPick": null,
+    "judged_at": "2026-09-19T16:01:30.355Z"
+  },
+  {
+    "id": "3736b9aea064",
+    "title": "Nature & Space Competition #9 — Shake-the-Snow-Globe Weather",
+    "prompt": "Build this as one complete, self-contained HTML file: A snow-globe weather visualizer you shake (click-drag) to trigger storms over an INVENTED tiny town; a dial cycles sun/rain/storm/snow with smooth transitions and the town reacts (umbrellas, lights). Reduced-motion aware. 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": "2026-09-19T16:06:31.911Z",
+    "winner": null,
+    "runs": [
+      {
+        "model": "mlx__qwen3-30b-a3b-instruct-2507-4bit",
+        "status": "error",
+        "error": "timeout after 600s",
+        "seconds": 600,
+        "cost": null,
+        "started_at": "2026-09-19T16:06:32.377Z",
+        "finished_at": "2026-09-19T16:16:32.740Z",
+        "queued_at": "2026-09-19T16:06:31.952Z"
+      },
+      {
+        "model": "exo__minimax-m2-7-4bit",
+        "status": "error",
+        "error": "openai-local bad response: 404",
+        "seconds": 0,
+        "cost": null,
+        "started_at": "2026-09-19T16:06:32.482Z",
+        "finished_at": "2026-09-19T16:06:32.681Z",
+        "queued_at": "2026-09-19T16:06:32.031Z"
+      },
+      {
+        "model": "qwen25-7b",
+        "status": "error",
+        "error": "timeout after 600s",
+        "seconds": 600,
+        "cost": null,
+        "started_at": "2026-09-19T16:06:32.579Z",
+        "finished_at": "2026-09-19T16:16:32.659Z",
+        "queued_at": "2026-09-19T16:06:32.102Z"
+      },
+      {
+        "model": "mlx__qwen3-next-80b-a3b-instruct-4bit",
+        "status": "error",
+        "error": "timeout after 600s",
+        "seconds": 600,
+        "cost": null,
+        "started_at": "2026-09-19T16:16:32.787Z",
+        "finished_at": "2026-09-19T16:26:32.876Z",
+        "queued_at": "2026-09-19T16:06:32.179Z"
+      },
+      {
+        "model": "exo__qwen3-coder-480b-a35b-instruct-4bit",
+        "status": "error",
+        "error": "openai-local bad response: 404",
+        "seconds": 0,
+        "cost": null,
+        "started_at": "2026-09-19T16:06:32.733Z",
+        "finished_at": "2026-09-19T16:06:32.806Z",
+        "queued_at": "2026-09-19T16:06:32.228Z"
+      },
+      {
+        "model": "mac1__minicpm-v-latest",
+        "status": "error",
+        "error": "timeout after 600s",
+        "seconds": 600,
+        "cost": null,
+        "started_at": "2026-09-19T16:16:32.700Z",
+        "finished_at": "2026-09-19T16:26:32.840Z",
+        "queued_at": "2026-09-19T16:06:32.287Z"
+      }
+    ]
   }
 ]
\ No newline at end of file
diff --git a/yolo/arena-loop-state.json b/yolo/arena-loop-state.json
index 40f4b52..68b80d1 100644
--- a/yolo/arena-loop-state.json
+++ b/yolo/arena-loop-state.json
@@ -1 +1 @@
-{"promptIdx":3,"modelOffset":124,"compCount":{"Art":18,"Culture":17,"News":17,"Political Cartoon":17,"Games":9,"Real Work":9,"Data Viz":9,"Science":9,"Music":9,"Sports":9,"History":8,"Nature & Space":8,"Comedy":8,"Demoscene":8,"Finance":8,"Design":8},"catIdx":10,"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":2,"Nature & Space":2,"Comedy":2,"Demoscene":2,"Finance":2,"Design":2}}
\ No newline at end of file
+{"promptIdx":3,"modelOffset":7,"compCount":{"Art":18,"Culture":17,"News":17,"Political Cartoon":17,"Games":9,"Real Work":9,"Data Viz":9,"Science":9,"Music":9,"Sports":9,"History":9,"Nature & Space":9,"Comedy":8,"Demoscene":8,"Finance":8,"Design":8},"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
diff --git a/yolo/daily-log.jsonl b/yolo/daily-log.jsonl
index e2e698b..1c2f82e 100644
--- a/yolo/daily-log.jsonl
+++ b/yolo/daily-log.jsonl
@@ -225,3 +225,5 @@
 {"ts":"2026-09-19T15:43:10.856Z","id":"1220d17b81ac","promptId":"cell","category":"Science","title":"Science Competition #9 — Cell as a Factory-City","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
 {"ts":"2026-09-19T15:48:19.363Z","id":"cb424bcb1c2f","promptId":"audioviz","category":"Music","title":"Music Competition #9 — Skyline Audio Visualizer","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
 {"ts":"2026-09-19T15:53:27.618Z","id":"b86882299834","promptId":"statcard","category":"Sports","title":"Sports Competition #9 — Holographic Stat Cards","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-19T16:01:31.845Z","id":"8255d17be8ed","promptId":"artifact","category":"History","title":"History Competition #9 — Spotlit Relic Viewer","models":6,"done":1,"errored":5,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-19T16:26:33.077Z","id":"3736b9aea064","promptId":"weather","category":"Nature & Space","title":"Nature & Space Competition #9 — Shake-the-Snow-Globe Weather","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}

← 2c3ef7e auto-data-snapshot: 2026-09-19T08:55:30 (3 data files) — dat  ·  back to Model Arena  ·  auto-data-snapshot: 2026-09-19T09:59:20 (3 data files) — dat 2599fea →