[object Object]

← back to Model Arena

auto-data-snapshot: 2026-09-25T12:54:38 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl

8af60a1f0b888634cb417a3b9a3228cedc860a04 · 2026-09-25 12:55:22 -0700 · auto-commit-fleet

Files touched

Diff

commit 8af60a1f0b888634cb417a3b9a3228cedc860a04
Author: auto-commit-fleet <steve@designerwallcoverings.com>
Date:   Fri Sep 25 12:55:22 2026 -0700

    auto-data-snapshot: 2026-09-25T12:54:38 (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 1a57cf9..d59ca38 100644
--- a/data/challenges.json
+++ b/data/challenges.json
@@ -93665,14 +93665,90 @@
       },
       {
         "model": "exo__qwen3-6-35b-a3b-bf16",
+        "status": "error",
+        "error": "timeout after 300s",
+        "seconds": 300,
+        "cost": null,
+        "started_at": "2026-09-25T19:24:11.415Z",
+        "finished_at": "2026-09-25T19:29:11.655Z",
+        "queued_at": "2026-09-25T19:14:10.481Z",
+        "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3-30B-A3B-Instruct-2507-4bit)"
+      }
+    ]
+  },
+  {
+    "id": "8213aaa70d96",
+    "title": "Real Work Competition #38 — Timesheet Garden",
+    "prompt": "Build this as one complete, self-contained HTML file: A timesheet that grows your week as a garden — each logged hour sprouts a plant in the right plot, overtime wilts, and an 'invoice' view harvests it into a clean printable total with rate math and validation. 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": "Real Work",
+    "designTools": false,
+    "created_at": "2026-09-25T19:34:15.592Z",
+    "winner": null,
+    "runs": [
+      {
+        "model": "exo__qwen3-vl-4b-instruct-4bit",
+        "status": "error",
+        "error": "timeout after 300s",
+        "seconds": 300,
+        "cost": null,
+        "started_at": "2026-09-25T19:34:15.796Z",
+        "finished_at": "2026-09-25T19:39:15.901Z",
+        "queued_at": "2026-09-25T19:34:15.624Z",
+        "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3-30B-A3B-Instruct-2507-4bit)"
+      },
+      {
+        "model": "exo__minimax-m2-7",
+        "status": "error",
+        "error": "timeout after 300s",
+        "seconds": 300,
+        "cost": null,
+        "started_at": "2026-09-25T19:39:15.939Z",
+        "finished_at": "2026-09-25T19:44:16.215Z",
+        "queued_at": "2026-09-25T19:34:15.657Z",
+        "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3-30B-A3B-Instruct-2507-4bit)"
+      },
+      {
+        "model": "exo__llama-3-3-70b-instruct-4bit",
+        "status": "error",
+        "error": "timeout after 300s",
+        "seconds": 300,
+        "cost": null,
+        "started_at": "2026-09-25T19:44:16.276Z",
+        "finished_at": "2026-09-25T19:49:16.550Z",
+        "queued_at": "2026-09-25T19:34:15.686Z",
+        "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3-30B-A3B-Instruct-2507-4bit)"
+      },
+      {
+        "model": "exo__gemma-4-e2b-it-bf16",
+        "status": "error",
+        "error": "timeout after 300s",
+        "seconds": 300,
+        "cost": null,
+        "started_at": "2026-09-25T19:49:16.611Z",
+        "finished_at": "2026-09-25T19:54:16.772Z",
+        "queued_at": "2026-09-25T19:34:15.716Z",
+        "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3-30B-A3B-Instruct-2507-4bit)"
+      },
+      {
+        "model": "exo__qwen3-next-80b-a3b-instruct-8bit",
         "status": "running",
         "error": null,
         "seconds": null,
         "cost": null,
-        "started_at": "2026-09-25T19:24:11.415Z",
+        "started_at": "2026-09-25T19:54:16.799Z",
         "finished_at": null,
-        "queued_at": "2026-09-25T19:14:10.481Z",
+        "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": "queued",
+        "error": null,
+        "seconds": null,
+        "cost": null,
+        "started_at": null,
+        "finished_at": null,
+        "queued_at": "2026-09-25T19:34:15.771Z"
       }
     ]
   }
diff --git a/yolo/arena-loop-state.json b/yolo/arena-loop-state.json
index 814e343..ef16eb3 100644
--- a/yolo/arena-loop-state.json
+++ b/yolo/arena-loop-state.json
@@ -1 +1 @@
-{"promptIdx":3,"modelOffset":14,"compCount":{"Art":76,"Culture":75,"News":75,"Political Cartoon":75,"Games":38,"Real Work":37,"Data Viz":37,"Science":37,"Music":37,"Sports":37,"History":37,"Nature & Space":37,"Comedy":37,"Demoscene":37,"Finance":37,"Design":37},"catIdx":5,"perCat":{"Art":3,"Culture":3,"News":3,"Political Cartoon":3,"Games":2,"Real Work":1,"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":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
diff --git a/yolo/daily-log.jsonl b/yolo/daily-log.jsonl
index 083fcf0..0848b6e 100644
--- a/yolo/daily-log.jsonl
+++ b/yolo/daily-log.jsonl
@@ -842,3 +842,4 @@
 {"ts":"2026-09-22T16:19:00.766Z","id":"0715b25a41dd","promptId":"languages","category":"Culture","title":"Culture Competition #75 — The Last Speaker","models":4,"done":4,"errored":0,"settled":true,"aiPick":null,"loop":true}
 {"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}

← ae020b8 auto-data-snapshot: 2026-09-25T12:23:56 (3 data files) — dat  ·  back to Model Arena  ·  auto-data-snapshot: 2026-09-25T13:25:27 (3 data files) — dat 309586e →