[object Object]

← back to Model Arena

auto-data-snapshot: 2026-09-27T03:31:43 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl

73f20e455ec101fb5bc37736550f798dd663591f · 2026-09-27 03:32:11 -0700 · auto-commit-fleet

Files touched

Diff

commit 73f20e455ec101fb5bc37736550f798dd663591f
Author: auto-commit-fleet <steve@designerwallcoverings.com>
Date:   Sun Sep 27 03:32:11 2026 -0700

    auto-data-snapshot: 2026-09-27T03:31:43 (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 4071a66..6e95148 100644
--- a/data/challenges.json
+++ b/data/challenges.json
@@ -96896,24 +96896,100 @@
       },
       {
         "model": "exo__glm-5-1-dq4plus-q8",
+        "status": "error",
+        "error": "timeout after 300s",
+        "seconds": 300,
+        "cost": null,
+        "started_at": "2026-09-27T09:57:42.272Z",
+        "finished_at": "2026-09-27T10:02:42.696Z",
+        "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": "error",
+        "error": "timeout after 300s",
+        "seconds": 301,
+        "cost": null,
+        "started_at": "2026-09-27T10:02:42.792Z",
+        "finished_at": "2026-09-27T10:07:43.596Z",
+        "queued_at": "2026-09-27T09:37:40.666Z",
+        "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)"
+      }
+    ]
+  },
+  {
+    "id": "93648dcc38ff",
+    "title": "Data Viz Competition #40 — City of Data Dashboard",
+    "prompt": "Build this as one complete, self-contained HTML file: An INVENTED 'city of data' dashboard where bar charts are skyscrapers, a donut is a roundabout, and a line chart is the dusk skyline — one shared filter re-zones the whole city, with a legend and an empty 'ghost town' state. 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": "2026-09-27T10:12:50.540Z",
+    "winner": null,
+    "runs": [
+      {
+        "model": "exo__gpt-oss-20b-mxfp4-q8",
+        "status": "error",
+        "error": "timeout after 300s",
+        "seconds": 300,
+        "cost": null,
+        "started_at": "2026-09-27T10:12:51.064Z",
+        "finished_at": "2026-09-27T10:17:51.321Z",
+        "queued_at": "2026-09-27T10:12:50.620Z",
+        "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)"
+      },
+      {
+        "model": "exo__nvidia-nemotron-3-nano-30b-a3b-mlx-bf16",
+        "status": "error",
+        "error": "timeout after 300s",
+        "seconds": 300,
+        "cost": null,
+        "started_at": "2026-09-27T10:17:51.369Z",
+        "finished_at": "2026-09-27T10:22:51.753Z",
+        "queued_at": "2026-09-27T10:12:50.705Z",
+        "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)"
+      },
+      {
+        "model": "exo__kimi-k2-7-code",
+        "status": "error",
+        "error": "openai-local bad response: 404",
+        "seconds": 0,
+        "cost": null,
+        "started_at": "2026-09-27T10:22:51.825Z",
+        "finished_at": "2026-09-27T10:22:52.001Z",
+        "queued_at": "2026-09-27T10:12:50.775Z"
+      },
+      {
+        "model": "exo__gemma-4-31b-it-bf16",
+        "status": "error",
+        "error": "timeout after 300s",
+        "seconds": 300,
+        "cost": null,
+        "started_at": "2026-09-27T10:22:52.059Z",
+        "finished_at": "2026-09-27T10:27:52.218Z",
+        "queued_at": "2026-09-27T10:12:50.869Z",
+        "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)"
+      },
+      {
+        "model": "exo__minimax-m2-1-3bit",
         "status": "running",
         "error": null,
         "seconds": null,
         "cost": null,
-        "started_at": "2026-09-27T09:57:42.272Z",
+        "started_at": "2026-09-27T10:27:52.264Z",
         "finished_at": null,
-        "queued_at": "2026-09-27T09:37:40.571Z",
+        "queued_at": "2026-09-27T10:12:50.934Z",
         "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)"
       },
       {
-        "model": "exo__llama-3-1-nemotron-nano-4b-v1-1-bf16",
+        "model": "exo__qwen3-5-397b-a17b-6bit",
         "status": "queued",
         "error": null,
         "seconds": null,
         "cost": null,
         "started_at": null,
         "finished_at": null,
-        "queued_at": "2026-09-27T09:37:40.666Z"
+        "queued_at": "2026-09-27T10:12:51.007Z"
       }
     ]
   }
diff --git a/yolo/arena-loop-state.json b/yolo/arena-loop-state.json
index 68b97d6..f953105 100644
--- a/yolo/arena-loop-state.json
+++ b/yolo/arena-loop-state.json
@@ -1 +1 @@
-{"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
+{"promptIdx":3,"modelOffset":93,"compCount":{"Art":80,"Culture":79,"News":79,"Political Cartoon":79,"Games":40,"Real Work":40,"Data Viz":40,"Science":39,"Music":39,"Sports":39,"History":39,"Nature & Space":39,"Comedy":39,"Demoscene":39,"Finance":39,"Design":39},"catIdx":7,"perCat":{"Art":3,"Culture":3,"News":3,"Political Cartoon":3,"Games":1,"Real Work":1,"Data Viz":1,"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 b68b093..c55142d 100644
--- a/yolo/daily-log.jsonl
+++ b/yolo/daily-log.jsonl
@@ -883,3 +883,4 @@
 {"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}
+{"ts":"2026-09-27T10:07:50.445Z","id":"b29928d41468","promptId":"crm","category":"Real Work","title":"Real Work Competition #40 — Fishing-Dock CRM","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}

← fa13df0 auto-data-snapshot: 2026-09-27T03:00:59 (3 data files) — dat  ·  back to Model Arena  ·  auto-data-snapshot: 2026-09-27T04:02:15 (3 data files) — dat e06e701 →