[object Object]

← back to Model Arena

auto-data-snapshot: 2026-09-27T20:59:25 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl

9bc0f9137d950dc2a1fe5e28007c48983cfe7adf · 2026-09-27 20:59:56 -0700 · auto-commit-fleet

Files touched

Diff

commit 9bc0f9137d950dc2a1fe5e28007c48983cfe7adf
Author: auto-commit-fleet <steve@designerwallcoverings.com>
Date:   Sun Sep 27 20:59:56 2026 -0700

    auto-data-snapshot: 2026-09-27T20:59:25 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl
---
 data/challenges.json       | 80 ++++++++++++++++++++++++++++++++++++++++++++--
 yolo/arena-loop-state.json |  2 +-
 yolo/daily-log.jsonl       |  1 +
 3 files changed, 80 insertions(+), 3 deletions(-)

diff --git a/data/challenges.json b/data/challenges.json
index 8aef316..12a65b6 100644
--- a/data/challenges.json
+++ b/data/challenges.json
@@ -99026,13 +99026,89 @@
       },
       {
         "model": "exo__deepseek-v4-pro",
+        "status": "error",
+        "error": "timeout after 300s",
+        "seconds": 300,
+        "cost": null,
+        "started_at": "2026-09-28T03:25:16.648Z",
+        "finished_at": "2026-09-28T03:30:16.927Z",
+        "queued_at": "2026-09-28T03:00:14.356Z",
+        "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3-30B-A3B-Instruct-2507-4bit)"
+      }
+    ]
+  },
+  {
+    "id": "2e454c06f75f",
+    "title": "Finance Competition #41 — 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": "2026-09-28T03:35:23.824Z",
+    "winner": null,
+    "runs": [
+      {
+        "model": "exo__deepseek-v3-1-8bit",
+        "status": "error",
+        "error": "timeout after 300s",
+        "seconds": 300,
+        "cost": null,
+        "started_at": "2026-09-28T03:35:24.067Z",
+        "finished_at": "2026-09-28T03:40:24.175Z",
+        "queued_at": "2026-09-28T03:35:23.858Z",
+        "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3-30B-A3B-Instruct-2507-4bit)"
+      },
+      {
+        "model": "exo__glm-5-8bit-mxfp8",
+        "status": "error",
+        "error": "timeout after 300s",
+        "seconds": 300,
+        "cost": null,
+        "started_at": "2026-09-28T03:40:24.246Z",
+        "finished_at": "2026-09-28T03:45:24.614Z",
+        "queued_at": "2026-09-28T03:35:23.888Z",
+        "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3-30B-A3B-Instruct-2507-4bit)"
+      },
+      {
+        "model": "exo__nvidia-nemotron-3-nano-30b-a3b-mlx-mxfp4",
+        "status": "error",
+        "error": "timeout after 300s",
+        "seconds": 300,
+        "cost": null,
+        "started_at": "2026-09-28T03:45:24.779Z",
+        "finished_at": "2026-09-28T03:50:25.135Z",
+        "queued_at": "2026-09-28T03:35:23.915Z",
+        "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3-30B-A3B-Instruct-2507-4bit)"
+      },
+      {
+        "model": "exo__llama-3-1-nemotron-nano-4b-v1-1-8bit",
+        "status": "error",
+        "error": "timeout after 300s",
+        "seconds": 301,
+        "cost": null,
+        "started_at": "2026-09-28T03:50:25.285Z",
+        "finished_at": "2026-09-28T03:55:25.970Z",
+        "queued_at": "2026-09-28T03:35:23.953Z",
+        "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3-30B-A3B-Instruct-2507-4bit)"
+      },
+      {
+        "model": "exo__kimi-k2-6",
+        "status": "error",
+        "error": "openai-local bad response: 404",
+        "seconds": 0,
+        "cost": null,
+        "started_at": "2026-09-28T03:55:26.178Z",
+        "finished_at": "2026-09-28T03:55:26.375Z",
+        "queued_at": "2026-09-28T03:35:23.990Z"
+      },
+      {
+        "model": "exo__nvidia-nemotron-3-nano-30b-a3b-mlx-8bit",
         "status": "running",
         "error": null,
         "seconds": null,
         "cost": null,
-        "started_at": "2026-09-28T03:25:16.648Z",
+        "started_at": "2026-09-28T03:55:26.477Z",
         "finished_at": null,
-        "queued_at": "2026-09-28T03:00:14.356Z",
+        "queued_at": "2026-09-28T03:35:24.023Z",
         "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3-30B-A3B-Instruct-2507-4bit)"
       }
     ]
diff --git a/yolo/arena-loop-state.json b/yolo/arena-loop-state.json
index 43aedbf..ad73850 100644
--- a/yolo/arena-loop-state.json
+++ b/yolo/arena-loop-state.json
@@ -1 +1 @@
-{"promptIdx":3,"modelOffset":124,"compCount":{"Art":82,"Culture":81,"News":81,"Political Cartoon":81,"Games":41,"Real Work":41,"Data Viz":41,"Science":41,"Music":41,"Sports":41,"History":41,"Nature & Space":41,"Comedy":41,"Demoscene":41,"Finance":40,"Design":40},"catIdx":14,"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":2,"Demoscene":2,"Finance":1,"Design":1}}
\ No newline at end of file
+{"promptIdx":3,"modelOffset":130,"compCount":{"Art":82,"Culture":81,"News":81,"Political Cartoon":81,"Games":41,"Real Work":41,"Data Viz":41,"Science":41,"Music":41,"Sports":41,"History":41,"Nature & Space":41,"Comedy":41,"Demoscene":41,"Finance":41,"Design":40},"catIdx":15,"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":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 82ff9e4..991cb09 100644
--- a/yolo/daily-log.jsonl
+++ b/yolo/daily-log.jsonl
@@ -909,3 +909,4 @@
 {"ts":"2026-09-28T01:44:53.007Z","id":"98cfc5a1ebdc","promptId":"empire-map","category":"History","title":"History Competition #41 — An Empire That Breathes","models":6,"done":1,"errored":5,"settled":true,"aiPick":null,"loop":true}
 {"ts":"2026-09-28T02:20:02.798Z","id":"c16b6f43d022","promptId":"ecosystem","category":"Nature & Space","title":"Nature & Space Competition #41 — Terrarium in a Jar","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
 {"ts":"2026-09-28T02:55:13.792Z","id":"ddcca631c6b6","promptId":"excuse","category":"Comedy","title":"Comedy Competition #41 — The Excuse Slot Machine","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-28T03:30:23.720Z","id":"fb497e0af585","promptId":"tunnel","category":"Demoscene","title":"Demoscene Competition #41 — Wormhole to Anywhere","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}

← c55d347 auto-data-snapshot: 2026-09-27T20:28:52 (2 data files) — dat  ·  back to Model Arena  ·  auto-data-snapshot: 2026-09-27T21:30:02 (3 data files) — dat 6a517b1 →