[object Object]

← back to Model Arena

auto-data-snapshot: 2026-09-26T09:40:15 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl

9c832150842c91d93955995e4768ddabd988569f · 2026-09-26 09:41:33 -0700 · auto-commit-fleet

Files touched

Diff

commit 9c832150842c91d93955995e4768ddabd988569f
Author: auto-commit-fleet <steve@designerwallcoverings.com>
Date:   Sat Sep 26 09:41:33 2026 -0700

    auto-data-snapshot: 2026-09-26T09:40:15 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl
---
 data/challenges.json       | 108 +++++++++++++++++++++++++++++++++++++--------
 yolo/arena-loop-state.json |   2 +-
 yolo/daily-log.jsonl       |   1 +
 3 files changed, 92 insertions(+), 19 deletions(-)

diff --git a/data/challenges.json b/data/challenges.json
index f141b11..0756f2f 100644
--- a/data/challenges.json
+++ b/data/challenges.json
@@ -94147,14 +94147,14 @@
       {
         "model": "exo__qwen3-5-122b-a10b-4bit",
         "status": "error",
-        "error": "server restarted mid-run",
+        "error": "server restarted mid-run (gave up after 4 resumes)",
         "seconds": 0,
         "cost": null,
         "started_at": "2026-09-26T15:38:20.872Z",
         "finished_at": null,
         "queued_at": "2026-09-26T15:38:20.429Z",
         "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3-30B-A3B-Instruct-2507-4bit)",
-        "resumes": 4
+        "resumes": 5
       },
       {
         "model": "mac1__qwen2-5vl-7b",
@@ -94170,46 +94170,46 @@
       {
         "model": "mlx__mlx-community-qwen3-30b-a3b-instruct-2507-4bit",
         "status": "error",
-        "error": "server restarted mid-run",
+        "error": "server restarted mid-run (gave up after 4 resumes)",
         "seconds": 0,
         "cost": null,
         "started_at": "2026-09-26T15:38:21.127Z",
         "finished_at": null,
         "queued_at": "2026-09-26T15:38:20.638Z",
-        "resumes": 4
+        "resumes": 5
       },
       {
         "model": "exo__gemma-4-26b-a4b-it-6bit",
         "status": "error",
-        "error": "server restarted mid-run",
+        "error": "server restarted mid-run (gave up after 4 resumes)",
         "seconds": 0,
         "cost": null,
         "started_at": null,
         "finished_at": null,
         "queued_at": "2026-09-26T15:38:20.712Z",
-        "resumes": 4
+        "resumes": 5
       },
       {
         "model": "exo__qwen3-6-35b-a3b-bf16",
         "status": "error",
-        "error": "server restarted mid-run",
+        "error": "server restarted mid-run (gave up after 4 resumes)",
         "seconds": 0,
         "cost": null,
         "started_at": null,
         "finished_at": null,
         "queued_at": "2026-09-26T15:38:20.745Z",
-        "resumes": 4
+        "resumes": 5
       },
       {
         "model": "exo__qwen3-vl-4b-instruct-4bit",
         "status": "error",
-        "error": "server restarted mid-run",
+        "error": "server restarted mid-run (gave up after 4 resumes)",
         "seconds": 0,
         "cost": null,
         "started_at": null,
         "finished_at": null,
         "queued_at": "2026-09-26T15:38:20.825Z",
-        "resumes": 4
+        "resumes": 5
       }
     ],
     "aiPick": null
@@ -94266,7 +94266,7 @@
         "finished_at": null,
         "queued_at": "2026-09-26T15:45:49.869Z",
         "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3-30B-A3B-Instruct-2507-4bit)",
-        "resumes": 1
+        "resumes": 2
       },
       {
         "model": "exo__gemma-4-e2b-it-bf16",
@@ -94277,7 +94277,7 @@
         "started_at": null,
         "finished_at": null,
         "queued_at": "2026-09-26T15:45:49.924Z",
-        "resumes": 1
+        "resumes": 2
       },
       {
         "model": "exo__qwen3-next-80b-a3b-instruct-8bit",
@@ -94288,7 +94288,7 @@
         "started_at": null,
         "finished_at": null,
         "queued_at": "2026-09-26T15:45:50.215Z",
-        "resumes": 1
+        "resumes": 2
       },
       {
         "model": "exo__qwen3-6-27b-4bit",
@@ -94299,7 +94299,7 @@
         "started_at": null,
         "finished_at": null,
         "queued_at": "2026-09-26T15:45:50.352Z",
-        "resumes": 1
+        "resumes": 2
       },
       {
         "model": "exo__glm-4-7-4bit",
@@ -94310,7 +94310,7 @@
         "started_at": null,
         "finished_at": null,
         "queued_at": "2026-09-26T15:45:50.626Z",
-        "resumes": 1
+        "resumes": 2
       }
     ],
     "aiPick": null
@@ -94381,14 +94381,86 @@
       },
       {
         "model": "exo__qwen3-next-80b-a3b-thinking-4bit",
+        "status": "error",
+        "error": "timeout after 300s",
+        "seconds": 316,
+        "cost": null,
+        "started_at": "2026-09-26T16:22:54.146Z",
+        "finished_at": "2026-09-26T16:28:11.354Z",
+        "queued_at": "2026-09-26T15:57:17.601Z",
+        "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3-30B-A3B-Instruct-2507-4bit)"
+      }
+    ]
+  },
+  {
+    "id": "07410865575d",
+    "title": "Finance Competition #38 — Meme-Stock Chart With a Personality",
+    "prompt": "Build this as one complete, self-contained HTML file: An INVENTED meme-stock candlestick chart that reacts to a 'hype' slider (rockets, panic), draws a moving average, shows a crosshair readout and volume, and has a fake pundit narrate the big moves. 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": "Finance",
+    "designTools": false,
+    "created_at": "2026-09-26T16:41:29.574Z",
+    "winner": null,
+    "runs": [
+      {
+        "model": "exo__deepseek-v3-1-4bit",
         "status": "running",
         "error": null,
         "seconds": null,
         "cost": null,
-        "started_at": "2026-09-26T16:22:54.146Z",
+        "started_at": "2026-09-26T16:41:30.464Z",
         "finished_at": null,
-        "queued_at": "2026-09-26T15:57:17.601Z",
-        "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3-30B-A3B-Instruct-2507-4bit)"
+        "queued_at": "2026-09-26T16:41:29.667Z",
+        "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)"
+      },
+      {
+        "model": "exo__llama-3-1-nemotron-70b-instruct-hf-8bit",
+        "status": "queued",
+        "error": null,
+        "seconds": null,
+        "cost": null,
+        "started_at": null,
+        "finished_at": null,
+        "queued_at": "2026-09-26T16:41:29.791Z"
+      },
+      {
+        "model": "exo__gemma-4-e4b-it-6bit",
+        "status": "queued",
+        "error": null,
+        "seconds": null,
+        "cost": null,
+        "started_at": null,
+        "finished_at": null,
+        "queued_at": "2026-09-26T16:41:29.840Z"
+      },
+      {
+        "model": "exo__nvidia-nemotron-3-nano-30b-a3b-mlx-5bit",
+        "status": "queued",
+        "error": null,
+        "seconds": null,
+        "cost": null,
+        "started_at": null,
+        "finished_at": null,
+        "queued_at": "2026-09-26T16:41:29.902Z"
+      },
+      {
+        "model": "exo__glm-4-7-flash-6bit",
+        "status": "queued",
+        "error": null,
+        "seconds": null,
+        "cost": null,
+        "started_at": null,
+        "finished_at": null,
+        "queued_at": "2026-09-26T16:41:30.199Z"
+      },
+      {
+        "model": "exo__qwen3-5-35b-a3b-8bit",
+        "status": "queued",
+        "error": null,
+        "seconds": null,
+        "cost": null,
+        "started_at": null,
+        "finished_at": null,
+        "queued_at": "2026-09-26T16:41:30.317Z"
       }
     ]
   }
diff --git a/yolo/arena-loop-state.json b/yolo/arena-loop-state.json
index 196ab07..dccae08 100644
--- a/yolo/arena-loop-state.json
+++ b/yolo/arena-loop-state.json
@@ -1 +1 @@
-{"promptIdx":3,"modelOffset":26,"compCount":{"Art":76,"Culture":75,"News":75,"Political Cartoon":75,"Games":38,"Real Work":38,"Data Viz":38,"Science":38,"Music":38,"Sports":38,"History":38,"Nature & Space":38,"Comedy":38,"Demoscene":38,"Finance":37,"Design":37},"catIdx":14,"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":1,"Design":1}}
\ No newline at end of file
+{"promptIdx":3,"modelOffset":32,"compCount":{"Art":76,"Culture":75,"News":75,"Political Cartoon":75,"Games":38,"Real Work":38,"Data Viz":38,"Science":38,"Music":38,"Sports":38,"History":38,"Nature & Space":38,"Comedy":38,"Demoscene":38,"Finance":38,"Design":37},"catIdx":15,"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":1}}
\ No newline at end of file
diff --git a/yolo/daily-log.jsonl b/yolo/daily-log.jsonl
index de2f10b..5c435a7 100644
--- a/yolo/daily-log.jsonl
+++ b/yolo/daily-log.jsonl
@@ -850,3 +850,4 @@
 {"ts":"2026-09-26T15:33:19.496Z","id":"53923fadf112","promptId":"empire-map","category":"History","title":"History Competition #38 — An Empire That Breathes","models":6,"done":2,"errored":4,"settled":true,"aiPick":null,"loop":true}
 {"ts":"2026-09-26T15:40:44.983Z","id":"58f3c99d2354","promptId":"ecosystem","category":"Nature & Space","title":"Nature & Space Competition #38 — Terrarium in a Jar","models":6,"done":1,"errored":5,"settled":true,"aiPick":null,"loop":true}
 {"ts":"2026-09-26T15:52:16.810Z","id":"f630bc9a0deb","promptId":"excuse","category":"Comedy","title":"Comedy Competition #38 — The Excuse Slot Machine","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-26T16:28:48.552Z","id":"b1f41a3c67fc","promptId":"tunnel","category":"Demoscene","title":"Demoscene Competition #38 — Wormhole to Anywhere","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}

← 4b88d13 auto-data-snapshot: 2026-09-26T09:21:27 (3 data files) — dat  ·  back to Model Arena  ·  auto-data-snapshot: 2026-09-26T10:11:45 (2 data files) — dat 00ee8c5 →