[object Object]

← back to Model Arena

auto-data-snapshot: 2026-09-26T18:52:13 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl

b2a23154a2eeb1863eb253b4ab9616a5bca2f5c4 · 2026-09-26 18:52:43 -0700 · auto-commit-fleet

Files touched

Diff

commit b2a23154a2eeb1863eb253b4ab9616a5bca2f5c4
Author: auto-commit-fleet <steve@designerwallcoverings.com>
Date:   Sat Sep 26 18:52:43 2026 -0700

    auto-data-snapshot: 2026-09-26T18:52:13 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl
---
 data/challenges.json       | 84 +++++++++++++++++++++++++++++++++++++++++++---
 yolo/arena-loop-state.json |  2 +-
 yolo/daily-log.jsonl       |  1 +
 3 files changed, 82 insertions(+), 5 deletions(-)

diff --git a/data/challenges.json b/data/challenges.json
index 129a1b0..0b5d26d 100644
--- a/data/challenges.json
+++ b/data/challenges.json
@@ -95603,24 +95603,100 @@
       },
       {
         "model": "exo__llama-3-1-nemotron-70b-instruct-hf-4bit",
+        "status": "error",
+        "error": "timeout after 300s",
+        "seconds": 300,
+        "cost": null,
+        "started_at": "2026-09-27T01:20:18.620Z",
+        "finished_at": "2026-09-27T01:25:19.126Z",
+        "queued_at": "2026-09-27T01:00:16.916Z",
+        "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)"
+      },
+      {
+        "model": "exo__deepseek-v4-flash",
+        "status": "error",
+        "error": "timeout after 300s",
+        "seconds": 300,
+        "cost": null,
+        "started_at": "2026-09-27T01:25:19.230Z",
+        "finished_at": "2026-09-27T01:30:19.666Z",
+        "queued_at": "2026-09-27T01:00:16.960Z",
+        "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)"
+      }
+    ]
+  },
+  {
+    "id": "7b0f6ffc48d4",
+    "title": "History Competition #39 — 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": "2026-09-27T01:35:20.136Z",
+    "winner": null,
+    "runs": [
+      {
+        "model": "exo__qwen3-next-80b-a3b-thinking-8bit",
+        "status": "error",
+        "error": "timeout after 300s",
+        "seconds": 300,
+        "cost": null,
+        "started_at": "2026-09-27T01:35:20.540Z",
+        "finished_at": "2026-09-27T01:40:20.681Z",
+        "queued_at": "2026-09-27T01:35:20.223Z",
+        "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)"
+      },
+      {
+        "model": "exo__deepseek-v4-pro",
+        "status": "error",
+        "error": "timeout after 300s",
+        "seconds": 300,
+        "cost": null,
+        "started_at": "2026-09-27T01:40:20.866Z",
+        "finished_at": "2026-09-27T01:45:21.269Z",
+        "queued_at": "2026-09-27T01:35:20.287Z",
+        "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)"
+      },
+      {
+        "model": "exo__deepseek-v3-1-8bit",
+        "status": "error",
+        "error": "timeout after 300s",
+        "seconds": 300,
+        "cost": null,
+        "started_at": "2026-09-27T01:45:21.320Z",
+        "finished_at": "2026-09-27T01:50:21.501Z",
+        "queued_at": "2026-09-27T01:35:20.340Z",
+        "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)"
+      },
+      {
+        "model": "exo__glm-5-8bit-mxfp8",
         "status": "running",
         "error": null,
         "seconds": null,
         "cost": null,
-        "started_at": "2026-09-27T01:20:18.620Z",
+        "started_at": "2026-09-27T01:50:21.543Z",
         "finished_at": null,
-        "queued_at": "2026-09-27T01:00:16.916Z",
+        "queued_at": "2026-09-27T01:35:20.393Z",
         "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)"
       },
       {
-        "model": "exo__deepseek-v4-flash",
+        "model": "exo__nvidia-nemotron-3-nano-30b-a3b-mlx-mxfp4",
+        "status": "queued",
+        "error": null,
+        "seconds": null,
+        "cost": null,
+        "started_at": null,
+        "finished_at": null,
+        "queued_at": "2026-09-27T01:35:20.438Z"
+      },
+      {
+        "model": "exo__llama-3-1-nemotron-nano-4b-v1-1-8bit",
         "status": "queued",
         "error": null,
         "seconds": null,
         "cost": null,
         "started_at": null,
         "finished_at": null,
-        "queued_at": "2026-09-27T01:00:16.960Z"
+        "queued_at": "2026-09-27T01:35:20.494Z"
       }
     ]
   }
diff --git a/yolo/arena-loop-state.json b/yolo/arena-loop-state.json
index 1917871..ec7a26e 100644
--- a/yolo/arena-loop-state.json
+++ b/yolo/arena-loop-state.json
@@ -1 +1 @@
-{"promptIdx":3,"modelOffset":122,"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":38,"Nature & Space":38,"Comedy":38,"Demoscene":38,"Finance":38,"Design":38},"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":128,"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":38,"Comedy":38,"Demoscene":38,"Finance":38,"Design":38},"catIdx":11,"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":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 904e6f6..05d0618 100644
--- a/yolo/daily-log.jsonl
+++ b/yolo/daily-log.jsonl
@@ -866,3 +866,4 @@
 {"ts":"2026-09-26T23:44:56.359Z","id":"850b8b67e16f","promptId":"scatter","category":"Data Viz","title":"Data Viz Competition #39 — Planet Dating Show","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
 {"ts":"2026-09-27T00:20:06.467Z","id":"77bf27d22094","promptId":"cell","category":"Science","title":"Science Competition #39 — Cell as a Factory-City","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
 {"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}

← 4d1555c auto-data-snapshot: 2026-09-26T18:21:31 (3 data files) — dat  ·  back to Model Arena  ·  auto-data-snapshot: 2026-09-26T19:22:47 (3 data files) — dat 84aa220 →