[object Object]

← back to Model Arena

auto-data-snapshot: 2026-09-27T05:03:58 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl

39b568d16478093751ccdb63b9636effa87002a0 · 2026-09-27 05:04:24 -0700 · auto-commit-fleet

Files touched

Diff

commit 39b568d16478093751ccdb63b9636effa87002a0
Author: auto-commit-fleet <steve@designerwallcoverings.com>
Date:   Sun Sep 27 05:04:24 2026 -0700

    auto-data-snapshot: 2026-09-27T05:03:58 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl
---
 data/challenges.json       | 88 ++++++++++++++++++++++++++++++++++++++++++----
 yolo/arena-loop-state.json |  2 +-
 yolo/daily-log.jsonl       |  1 +
 3 files changed, 84 insertions(+), 7 deletions(-)

diff --git a/data/challenges.json b/data/challenges.json
index fc86120..30ea729 100644
--- a/data/challenges.json
+++ b/data/challenges.json
@@ -97115,34 +97115,110 @@
       },
       {
         "model": "exo__kimi-k2-thinking",
+        "status": "error",
+        "error": "timeout after 300s",
+        "seconds": 300,
+        "cost": null,
+        "started_at": "2026-09-27T11:33:15.481Z",
+        "finished_at": "2026-09-27T11:38:15.864Z",
+        "queued_at": "2026-09-27T11:18:12.256Z",
+        "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)"
+      },
+      {
+        "model": "exo__qwen3-coder-next-bf16",
+        "status": "error",
+        "error": "timeout after 300s",
+        "seconds": 300,
+        "cost": null,
+        "started_at": "2026-09-27T11:38:16.091Z",
+        "finished_at": "2026-09-27T11:43:16.753Z",
+        "queued_at": "2026-09-27T11:18:12.432Z",
+        "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)"
+      },
+      {
+        "model": "exo__deepseek-v3-2-4bit",
+        "status": "error",
+        "error": "timeout after 300s",
+        "seconds": 301,
+        "cost": null,
+        "started_at": "2026-09-27T11:43:17.108Z",
+        "finished_at": "2026-09-27T11:48:17.748Z",
+        "queued_at": "2026-09-27T11:18:12.571Z",
+        "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)"
+      }
+    ]
+  },
+  {
+    "id": "f69c027db6a5",
+    "title": "Sports Competition #40 — Zero-G Relay League",
+    "prompt": "Build this as one complete, self-contained HTML file: A standings tracker for an INVENTED sport (zero-gravity relay) with a sortable table, a form guide of tiny animated results, and a team page that shows their home 'arena' as a themed backdrop. 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": "Sports",
+    "designTools": false,
+    "created_at": "2026-09-27T11:53:24.794Z",
+    "winner": null,
+    "runs": [
+      {
+        "model": "exo__nvidia-nemotron-nano-9b-v2-6bit",
+        "status": "error",
+        "error": "timeout after 300s",
+        "seconds": 300,
+        "cost": null,
+        "started_at": "2026-09-27T11:53:25.384Z",
+        "finished_at": "2026-09-27T11:58:25.621Z",
+        "queued_at": "2026-09-27T11:53:24.957Z",
+        "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)"
+      },
+      {
+        "model": "exo__meta-llama-3-1-8b-instruct-bf16",
+        "status": "error",
+        "error": "timeout after 300s",
+        "seconds": 300,
+        "cost": null,
+        "started_at": "2026-09-27T11:58:25.854Z",
+        "finished_at": "2026-09-27T12:03:26.289Z",
+        "queued_at": "2026-09-27T11:53:25.028Z",
+        "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)"
+      },
+      {
+        "model": "exo__gemma-4-e4b-it-bf16",
         "status": "running",
         "error": null,
         "seconds": null,
         "cost": null,
-        "started_at": "2026-09-27T11:33:15.481Z",
+        "started_at": "2026-09-27T12:03:26.642Z",
         "finished_at": null,
-        "queued_at": "2026-09-27T11:18:12.256Z",
+        "queued_at": "2026-09-27T11:53:25.094Z",
         "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)"
       },
       {
-        "model": "exo__qwen3-coder-next-bf16",
+        "model": "exo__qwen3-5-397b-a17b-4bit",
         "status": "queued",
         "error": null,
         "seconds": null,
         "cost": null,
         "started_at": null,
         "finished_at": null,
-        "queued_at": "2026-09-27T11:18:12.432Z"
+        "queued_at": "2026-09-27T11:53:25.161Z"
       },
       {
-        "model": "exo__deepseek-v3-2-4bit",
+        "model": "exo__glm-4-5-air-bf16",
+        "status": "queued",
+        "error": null,
+        "seconds": null,
+        "cost": null,
+        "started_at": null,
+        "finished_at": null,
+        "queued_at": "2026-09-27T11:53:25.223Z"
+      },
+      {
+        "model": "exo__qwen3-next-80b-a3b-instruct-4bit",
         "status": "queued",
         "error": null,
         "seconds": null,
         "cost": null,
         "started_at": null,
         "finished_at": null,
-        "queued_at": "2026-09-27T11:18:12.571Z"
+        "queued_at": "2026-09-27T11:53:25.279Z"
       }
     ]
   }
diff --git a/yolo/arena-loop-state.json b/yolo/arena-loop-state.json
index 4c33cf3..1803a71 100644
--- a/yolo/arena-loop-state.json
+++ b/yolo/arena-loop-state.json
@@ -1 +1 @@
-{"promptIdx":3,"modelOffset":105,"compCount":{"Art":80,"Culture":79,"News":79,"Political Cartoon":79,"Games":40,"Real Work":40,"Data Viz":40,"Science":40,"Music":40,"Sports":39,"History":39,"Nature & Space":39,"Comedy":39,"Demoscene":39,"Finance":39,"Design":39},"catIdx":9,"perCat":{"Art":3,"Culture":3,"News":3,"Political Cartoon":3,"Games":1,"Real Work":1,"Data Viz":1,"Science":1,"Music":1,"Sports":3,"History":3,"Nature & Space":3,"Comedy":3,"Demoscene":3,"Finance":3,"Design":3}}
\ No newline at end of file
+{"promptIdx":3,"modelOffset":111,"compCount":{"Art":80,"Culture":79,"News":79,"Political Cartoon":79,"Games":40,"Real Work":40,"Data Viz":40,"Science":40,"Music":40,"Sports":40,"History":39,"Nature & Space":39,"Comedy":39,"Demoscene":39,"Finance":39,"Design":39},"catIdx":10,"perCat":{"Art":3,"Culture":3,"News":3,"Political Cartoon":3,"Games":1,"Real Work":1,"Data Viz":1,"Science":1,"Music":1,"Sports":1,"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 4bfa1a1..27f0a52 100644
--- a/yolo/daily-log.jsonl
+++ b/yolo/daily-log.jsonl
@@ -886,3 +886,4 @@
 {"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}
 {"ts":"2026-09-27T10:37:56.992Z","id":"93648dcc38ff","promptId":"multi-chart","category":"Data Viz","title":"Data Viz Competition #40 — City of Data Dashboard","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
 {"ts":"2026-09-27T11:13:11.050Z","id":"403b88e8b45b","promptId":"solar","category":"Science","title":"Science Competition #40 — Conduct the Solar System","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
+{"ts":"2026-09-27T11:48:24.689Z","id":"53971a0c131a","promptId":"sequencer","category":"Music","title":"Music Competition #40 — Constellation Sequencer","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}

← 60a5edf auto-data-snapshot: 2026-09-27T04:32:44 (3 data files) — dat  ·  back to Model Arena  ·  auto-data-snapshot: 2026-09-27T05:34:27 (3 data files) — dat 9d5f935 →