[object Object]

← back to Model Arena

auto-data-snapshot: 2026-09-25T13:25:27 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl

309586e854609ab98ecae90bc72dca09b0eb7716 · 2026-09-25 13:25:58 -0700 · auto-commit-fleet

Files touched

Diff

commit 309586e854609ab98ecae90bc72dca09b0eb7716
Author: auto-commit-fleet <steve@designerwallcoverings.com>
Date:   Fri Sep 25 13:25:58 2026 -0700

    auto-data-snapshot: 2026-09-25T13:25:27 (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 d59ca38..fd29400 100644
--- a/data/challenges.json
+++ b/data/challenges.json
@@ -93731,24 +93731,100 @@
       },
       {
         "model": "exo__qwen3-next-80b-a3b-instruct-8bit",
+        "status": "error",
+        "error": "timeout after 300s",
+        "seconds": 300,
+        "cost": null,
+        "started_at": "2026-09-25T19:54:16.799Z",
+        "finished_at": "2026-09-25T19:59:16.921Z",
+        "queued_at": "2026-09-25T19:34:15.744Z",
+        "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3-30B-A3B-Instruct-2507-4bit)"
+      },
+      {
+        "model": "exo__qwen3-6-27b-4bit",
+        "status": "error",
+        "error": "timeout after 300s",
+        "seconds": 300,
+        "cost": null,
+        "started_at": "2026-09-25T19:59:17.169Z",
+        "finished_at": "2026-09-25T20:04:17.770Z",
+        "queued_at": "2026-09-25T19:34:15.771Z",
+        "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3-30B-A3B-Instruct-2507-4bit)"
+      }
+    ]
+  },
+  {
+    "id": "833c05408dfb",
+    "title": "Data Viz Competition #38 — Bean-to-Cup Sankey",
+    "prompt": "Build this as one complete, self-contained HTML file: An SVG sankey where an INVENTED coffee empire's beans flow from farm to cup — hover any stream to trace it, click to reroute supply and watch downstream totals update, with an accessible table fallback. 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": "Data Viz",
+    "designTools": false,
+    "created_at": "2026-09-25T20:09:28.023Z",
+    "winner": null,
+    "runs": [
+      {
+        "model": "exo__glm-4-7-4bit",
+        "status": "error",
+        "error": "timeout after 300s",
+        "seconds": 301,
+        "cost": null,
+        "started_at": "2026-09-25T20:09:29.882Z",
+        "finished_at": "2026-09-25T20:14:31.586Z",
+        "queued_at": "2026-09-25T20:09:28.774Z",
+        "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3-30B-A3B-Instruct-2507-4bit)"
+      },
+      {
+        "model": "exo__gemma-4-31b-it-4bit",
+        "status": "error",
+        "error": "timeout after 300s",
+        "seconds": 301,
+        "cost": null,
+        "started_at": "2026-09-25T20:14:31.657Z",
+        "finished_at": "2026-09-25T20:19:32.599Z",
+        "queued_at": "2026-09-25T20:09:29.151Z",
+        "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3-30B-A3B-Instruct-2507-4bit)"
+      },
+      {
+        "model": "exo__nvidia-nemotron-3-nano-30b-a3b-mlx-4bit",
+        "status": "error",
+        "error": "timeout after 300s",
+        "seconds": 304,
+        "cost": null,
+        "started_at": "2026-09-25T20:19:32.876Z",
+        "finished_at": "2026-09-25T20:24:36.983Z",
+        "queued_at": "2026-09-25T20:09:29.239Z",
+        "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3-30B-A3B-Instruct-2507-4bit)"
+      },
+      {
+        "model": "exo__llama-3-1-nemotron-nano-4b-v1-1-4bit",
         "status": "running",
         "error": null,
         "seconds": null,
         "cost": null,
-        "started_at": "2026-09-25T19:54:16.799Z",
+        "started_at": "2026-09-25T20:24:37.029Z",
         "finished_at": null,
-        "queued_at": "2026-09-25T19:34:15.744Z",
+        "queued_at": "2026-09-25T20:09:29.544Z",
         "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3-30B-A3B-Instruct-2507-4bit)"
       },
       {
-        "model": "exo__qwen3-6-27b-4bit",
+        "model": "exo__qwen3-coder-next-6bit",
+        "status": "queued",
+        "error": null,
+        "seconds": null,
+        "cost": null,
+        "started_at": null,
+        "finished_at": null,
+        "queued_at": "2026-09-25T20:09:29.729Z"
+      },
+      {
+        "model": "exo__step-3-5-flash-6bit",
         "status": "queued",
         "error": null,
         "seconds": null,
         "cost": null,
         "started_at": null,
         "finished_at": null,
-        "queued_at": "2026-09-25T19:34:15.771Z"
+        "queued_at": "2026-09-25T20:09:29.804Z"
       }
     ]
   }
diff --git a/yolo/arena-loop-state.json b/yolo/arena-loop-state.json
index ef16eb3..cf6cf13 100644
--- a/yolo/arena-loop-state.json
+++ b/yolo/arena-loop-state.json
@@ -1 +1 @@
-{"promptIdx":3,"modelOffset":20,"compCount":{"Art":76,"Culture":75,"News":75,"Political Cartoon":75,"Games":38,"Real Work":38,"Data Viz":37,"Science":37,"Music":37,"Sports":37,"History":37,"Nature & Space":37,"Comedy":37,"Demoscene":37,"Finance":37,"Design":37},"catIdx":6,"perCat":{"Art":3,"Culture":3,"News":3,"Political Cartoon":3,"Games":2,"Real Work":2,"Data Viz":1,"Science":1,"Music":1,"Sports":1,"History":1,"Nature & Space":1,"Comedy":1,"Demoscene":1,"Finance":1,"Design":1}}
\ No newline at end of file
+{"promptIdx":3,"modelOffset":26,"compCount":{"Art":76,"Culture":75,"News":75,"Political Cartoon":75,"Games":38,"Real Work":38,"Data Viz":38,"Science":37,"Music":37,"Sports":37,"History":37,"Nature & Space":37,"Comedy":37,"Demoscene":37,"Finance":37,"Design":37},"catIdx":7,"perCat":{"Art":3,"Culture":3,"News":3,"Political Cartoon":3,"Games":2,"Real Work":2,"Data Viz":2,"Science":1,"Music":1,"Sports":1,"History":1,"Nature & Space":1,"Comedy":1,"Demoscene":1,"Finance":1,"Design":1}}
\ No newline at end of file
diff --git a/yolo/daily-log.jsonl b/yolo/daily-log.jsonl
index 0848b6e..d1b72ee 100644
--- a/yolo/daily-log.jsonl
+++ b/yolo/daily-log.jsonl
@@ -843,3 +843,4 @@
 {"ts":"2026-09-22T16:24:34.034Z","id":"74a9c3f65798","promptId":"news-ticker","category":"News","title":"News Competition #75 — Absurd 24-Hour News","models":4,"done":4,"errored":0,"settled":true,"aiPick":null,"loop":true}
 {"ts":"2026-09-25T19:09:09.664Z","id":"acc2c9f4a253","promptId":"metaphor","category":"Political Cartoon","title":"Political Cartoon Competition #75 — Ship of State by Committee","models":6,"done":2,"errored":4,"settled":true,"aiPick":null,"loop":true}
 {"ts":"2026-09-25T19:29:15.465Z","id":"cd267a104b77","promptId":"breakout","category":"Games","title":"Games Competition #38 — Wake the Dragon Breakout","models":6,"done":1,"errored":5,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-25T20:04:25.488Z","id":"8213aaa70d96","promptId":"timesheet","category":"Real Work","title":"Real Work Competition #38 — Timesheet Garden","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}

← 8af60a1 auto-data-snapshot: 2026-09-25T12:54:38 (3 data files) — dat  ·  back to Model Arena  ·  auto-data-snapshot: 2026-09-25T13:56:04 (3 data files) — dat 70dec26 →