[object Object]

← back to Model Arena

auto-data-snapshot: 2026-09-27T03:00:59 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl

fa13df08ae967e7f5020989675b65204a1a950f2 · 2026-09-27 03:01:28 -0700 · auto-commit-fleet

Files touched

Diff

commit fa13df08ae967e7f5020989675b65204a1a950f2
Author: auto-commit-fleet <steve@designerwallcoverings.com>
Date:   Sun Sep 27 03:01:28 2026 -0700

    auto-data-snapshot: 2026-09-27T03:00:59 (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 0f4b30b..4071a66 100644
--- a/data/challenges.json
+++ b/data/challenges.json
@@ -96830,14 +96830,90 @@
       },
       {
         "model": "exo__qwen3-5-122b-a10b-bf16",
+        "status": "error",
+        "error": "timeout after 300s",
+        "seconds": 300,
+        "cost": null,
+        "started_at": "2026-09-27T09:27:31.859Z",
+        "finished_at": "2026-09-27T09:32:32.131Z",
+        "queued_at": "2026-09-27T09:02:29.577Z",
+        "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)"
+      }
+    ]
+  },
+  {
+    "id": "b29928d41468",
+    "title": "Real Work Competition #40 — Fishing-Dock CRM",
+    "prompt": "Build this as one complete, self-contained HTML file: A CRM where each lead is a fish on a line you drag between stages (Nibble -> Hooked -> Landed), per-stage totals shown as a catch tally, with search, quick-add, and validation. Playful but genuinely usable. 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": "2026-09-27T09:37:40.121Z",
+    "winner": null,
+    "runs": [
+      {
+        "model": "exo__gpt-oss-120b-mxfp4-q8",
+        "status": "error",
+        "error": "timeout after 300s",
+        "seconds": 300,
+        "cost": null,
+        "started_at": "2026-09-27T09:37:40.741Z",
+        "finished_at": "2026-09-27T09:42:41.242Z",
+        "queued_at": "2026-09-27T09:37:40.230Z",
+        "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)"
+      },
+      {
+        "model": "exo__qwen3-6-27b-bf16",
+        "status": "error",
+        "error": "timeout after 300s",
+        "seconds": 300,
+        "cost": null,
+        "started_at": "2026-09-27T09:42:41.301Z",
+        "finished_at": "2026-09-27T09:47:41.486Z",
+        "queued_at": "2026-09-27T09:37:40.308Z",
+        "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)"
+      },
+      {
+        "model": "exo__glm-4-7-flash-8bit",
+        "status": "error",
+        "error": "timeout after 300s",
+        "seconds": 300,
+        "cost": null,
+        "started_at": "2026-09-27T09:47:41.540Z",
+        "finished_at": "2026-09-27T09:52:41.717Z",
+        "queued_at": "2026-09-27T09:37:40.398Z",
+        "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)"
+      },
+      {
+        "model": "exo__gemma-4-e2b-it-4bit",
+        "status": "error",
+        "error": "timeout after 300s",
+        "seconds": 300,
+        "cost": null,
+        "started_at": "2026-09-27T09:52:41.785Z",
+        "finished_at": "2026-09-27T09:57:42.024Z",
+        "queued_at": "2026-09-27T09:37:40.478Z",
+        "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)"
+      },
+      {
+        "model": "exo__glm-5-1-dq4plus-q8",
         "status": "running",
         "error": null,
         "seconds": null,
         "cost": null,
-        "started_at": "2026-09-27T09:27:31.859Z",
+        "started_at": "2026-09-27T09:57:42.272Z",
         "finished_at": null,
-        "queued_at": "2026-09-27T09:02:29.577Z",
+        "queued_at": "2026-09-27T09:37:40.571Z",
         "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)"
+      },
+      {
+        "model": "exo__llama-3-1-nemotron-nano-4b-v1-1-bf16",
+        "status": "queued",
+        "error": null,
+        "seconds": null,
+        "cost": null,
+        "started_at": null,
+        "finished_at": null,
+        "queued_at": "2026-09-27T09:37:40.666Z"
       }
     ]
   }
diff --git a/yolo/arena-loop-state.json b/yolo/arena-loop-state.json
index 2f3de53..68b97d6 100644
--- a/yolo/arena-loop-state.json
+++ b/yolo/arena-loop-state.json
@@ -1 +1 @@
-{"promptIdx":3,"modelOffset":81,"compCount":{"Art":80,"Culture":79,"News":79,"Political Cartoon":79,"Games":40,"Real Work":39,"Data Viz":39,"Science":39,"Music":39,"Sports":39,"History":39,"Nature & Space":39,"Comedy":39,"Demoscene":39,"Finance":39,"Design":39},"catIdx":5,"perCat":{"Art":3,"Culture":3,"News":3,"Political Cartoon":3,"Games":1,"Real Work":3,"Data Viz":3,"Science":3,"Music":3,"Sports":3,"History":3,"Nature & Space":3,"Comedy":3,"Demoscene":3,"Finance":3,"Design":3}}
\ No newline at end of file
+{"promptIdx":3,"modelOffset":87,"compCount":{"Art":80,"Culture":79,"News":79,"Political Cartoon":79,"Games":40,"Real Work":40,"Data Viz":39,"Science":39,"Music":39,"Sports":39,"History":39,"Nature & Space":39,"Comedy":39,"Demoscene":39,"Finance":39,"Design":39},"catIdx":6,"perCat":{"Art":3,"Culture":3,"News":3,"Political Cartoon":3,"Games":1,"Real Work":1,"Data Viz":3,"Science":3,"Music":3,"Sports":3,"History":3,"Nature & Space":3,"Comedy":3,"Demoscene":3,"Finance":3,"Design":3}}
\ No newline at end of file
diff --git a/yolo/daily-log.jsonl b/yolo/daily-log.jsonl
index ef47635..b68b093 100644
--- a/yolo/daily-log.jsonl
+++ b/yolo/daily-log.jsonl
@@ -882,3 +882,4 @@
 {"ts":"2026-09-27T08:22:18.635Z","id":"3eeca9af985e","promptId":"news-ticker","category":"News","title":"News Competition #79 — Absurd 24-Hour News","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
 {"ts":"2026-09-27T08:57:28.883Z","id":"faace762ff30","promptId":"metaphor","category":"Political Cartoon","title":"Political Cartoon Competition #79 — Ship of State by Committee","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
 {"ts":"2026-09-27T09:04:02.990Z","id":"fcf664ddbe62","promptId":"compare","title":"Daily · Decision Tools: Model Comparison Console","done":2,"aiPick":null,"partial":false}
+{"ts":"2026-09-27T09:32:40.022Z","id":"5b15c17380c0","promptId":"snake","category":"Games","title":"Games Competition #40 — Comet Snake in a Dying Galaxy","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}

← af97759 auto-data-snapshot: 2026-09-27T02:30:26 (3 data files) — dat  ·  back to Model Arena  ·  auto-data-snapshot: 2026-09-27T03:31:43 (3 data files) — dat 73f20e4 →