[object Object]

← back to Model Arena

auto-data-snapshot: 2026-09-27T18:26:05 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl

e5f6ae40195fc5168c2e9044e6e6cf28b912ce77 · 2026-09-27 18:26:47 -0700 · auto-commit-fleet

Files touched

Diff

commit e5f6ae40195fc5168c2e9044e6e6cf28b912ce77
Author: auto-commit-fleet <steve@designerwallcoverings.com>
Date:   Sun Sep 27 18:26:47 2026 -0700

    auto-data-snapshot: 2026-09-27T18:26:05 (3 data files) — data/challenges.json yolo/arena-loop-state.json yolo/daily-log.jsonl
---
 data/challenges.json       | 159 ++++++++++++++++++++++++++++++++++-----------
 yolo/arena-loop-state.json |   2 +-
 yolo/daily-log.jsonl       |   1 +
 3 files changed, 122 insertions(+), 40 deletions(-)

diff --git a/data/challenges.json b/data/challenges.json
index 5055936..d09a282 100644
--- a/data/challenges.json
+++ b/data/challenges.json
@@ -94259,58 +94259,58 @@
       {
         "model": "exo__llama-3-3-70b-instruct-4bit",
         "status": "error",
-        "error": "server restarted mid-run",
+        "error": "server restarted mid-run (gave up after 4 resumes)",
         "seconds": 0,
         "cost": null,
         "started_at": "2026-09-26T15:50:52.257Z",
         "finished_at": null,
         "queued_at": "2026-09-26T15:45:49.869Z",
         "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3-30B-A3B-Instruct-2507-4bit)",
-        "resumes": 4
+        "resumes": 5
       },
       {
         "model": "exo__gemma-4-e2b-it-bf16",
         "status": "error",
-        "error": "server restarted mid-run",
+        "error": "server restarted mid-run (gave up after 4 resumes)",
         "seconds": 0,
         "cost": null,
         "started_at": null,
         "finished_at": null,
         "queued_at": "2026-09-26T15:45:49.924Z",
-        "resumes": 4
+        "resumes": 5
       },
       {
         "model": "exo__qwen3-next-80b-a3b-instruct-8bit",
         "status": "error",
-        "error": "server restarted mid-run",
+        "error": "server restarted mid-run (gave up after 4 resumes)",
         "seconds": 0,
         "cost": null,
         "started_at": null,
         "finished_at": null,
         "queued_at": "2026-09-26T15:45:50.215Z",
-        "resumes": 4
+        "resumes": 5
       },
       {
         "model": "exo__qwen3-6-27b-4bit",
         "status": "error",
-        "error": "server restarted mid-run",
+        "error": "server restarted mid-run (gave up after 4 resumes)",
         "seconds": 0,
         "cost": null,
         "started_at": null,
         "finished_at": null,
         "queued_at": "2026-09-26T15:45:50.352Z",
-        "resumes": 4
+        "resumes": 5
       },
       {
         "model": "exo__glm-4-7-4bit",
         "status": "error",
-        "error": "server restarted mid-run",
+        "error": "server restarted mid-run (gave up after 4 resumes)",
         "seconds": 0,
         "cost": null,
         "started_at": null,
         "finished_at": null,
         "queued_at": "2026-09-26T15:45:50.626Z",
-        "resumes": 4
+        "resumes": 5
       }
     ],
     "aiPick": null
@@ -94499,7 +94499,7 @@
         "finished_at": null,
         "queued_at": "2026-09-26T17:16:37.552Z",
         "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)",
-        "resumes": 2
+        "resumes": 3
       },
       {
         "model": "exo__kimi-k2-5",
@@ -94510,7 +94510,7 @@
         "started_at": null,
         "finished_at": null,
         "queued_at": "2026-09-26T17:16:37.599Z",
-        "resumes": 2
+        "resumes": 3
       },
       {
         "model": "exo__qwen3-5-397b-a17b-8bit",
@@ -94521,7 +94521,7 @@
         "started_at": null,
         "finished_at": null,
         "queued_at": "2026-09-26T17:16:37.654Z",
-        "resumes": 2
+        "resumes": 3
       },
       {
         "model": "exo__minimax-m2-7-5bit",
@@ -94532,7 +94532,7 @@
         "started_at": null,
         "finished_at": null,
         "queued_at": "2026-09-26T17:16:37.705Z",
-        "resumes": 2
+        "resumes": 3
       },
       {
         "model": "exo__qwen3-5-2b-mlx-8bit",
@@ -94543,7 +94543,7 @@
         "started_at": null,
         "finished_at": null,
         "queued_at": "2026-09-26T17:16:37.738Z",
-        "resumes": 2
+        "resumes": 3
       }
     ],
     "aiPick": null
@@ -97777,7 +97777,7 @@
         "finished_at": null,
         "queued_at": "2026-09-27T15:14:08.830Z",
         "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3.8-27B-8bit)",
-        "resumes": 1
+        "resumes": 2
       }
     ],
     "aiPick": null
@@ -97800,7 +97800,7 @@
         "started_at": null,
         "finished_at": null,
         "queued_at": "2026-09-27T15:41:36.332Z",
-        "resumes": 1
+        "resumes": 2
       },
       {
         "model": "exo__llama-3-1-nemotron-70b-instruct-hf-8bit",
@@ -97811,7 +97811,7 @@
         "started_at": null,
         "finished_at": null,
         "queued_at": "2026-09-27T15:41:36.403Z",
-        "resumes": 1
+        "resumes": 2
       },
       {
         "model": "exo__gemma-4-e4b-it-6bit",
@@ -97822,7 +97822,7 @@
         "started_at": null,
         "finished_at": null,
         "queued_at": "2026-09-27T15:41:36.475Z",
-        "resumes": 1
+        "resumes": 2
       },
       {
         "model": "exo__nvidia-nemotron-3-nano-30b-a3b-mlx-5bit",
@@ -97833,7 +97833,7 @@
         "started_at": null,
         "finished_at": null,
         "queued_at": "2026-09-27T15:41:36.553Z",
-        "resumes": 1
+        "resumes": 2
       },
       {
         "model": "exo__glm-4-7-flash-6bit",
@@ -97844,7 +97844,7 @@
         "started_at": null,
         "finished_at": null,
         "queued_at": "2026-09-27T15:41:36.628Z",
-        "resumes": 1
+        "resumes": 2
       },
       {
         "model": "exo__qwen3-5-35b-a3b-8bit",
@@ -97855,7 +97855,7 @@
         "started_at": null,
         "finished_at": null,
         "queued_at": "2026-09-27T15:41:36.690Z",
-        "resumes": 1
+        "resumes": 2
       }
     ],
     "aiPick": null
@@ -98655,63 +98655,144 @@
     "runs": [
       {
         "model": "exo__glm-5",
-        "status": "queued",
-        "error": null,
-        "seconds": null,
+        "status": "error",
+        "error": "server restarted mid-run",
+        "seconds": 0,
         "cost": null,
         "started_at": null,
         "finished_at": null,
-        "queued_at": "2026-09-28T00:55:54.688Z"
+        "queued_at": "2026-09-28T00:55:54.688Z",
+        "resumes": 1
       },
       {
         "model": "exo__nvidia-nemotron-nano-9b-v2-4bits",
-        "status": "queued",
-        "error": null,
-        "seconds": null,
+        "status": "error",
+        "error": "server restarted mid-run",
+        "seconds": 0,
         "cost": null,
         "started_at": null,
         "finished_at": null,
-        "queued_at": "2026-09-28T00:55:54.741Z"
+        "queued_at": "2026-09-28T00:55:54.741Z",
+        "resumes": 1
       },
       {
         "model": "exo__gemma-4-26b-a4b-it-bf16",
-        "status": "queued",
-        "error": null,
-        "seconds": null,
+        "status": "error",
+        "error": "server restarted mid-run",
+        "seconds": 0,
         "cost": null,
         "started_at": null,
         "finished_at": null,
-        "queued_at": "2026-09-28T00:55:54.775Z"
+        "queued_at": "2026-09-28T00:55:54.775Z",
+        "resumes": 1
       },
       {
         "model": "exo__meta-llama-3-1-70b-instruct-4bit",
+        "status": "error",
+        "error": "server restarted mid-run",
+        "seconds": 0,
+        "cost": null,
+        "started_at": null,
+        "finished_at": null,
+        "queued_at": "2026-09-28T00:55:54.807Z",
+        "resumes": 1
+      },
+      {
+        "model": "exo__qwen3-5-35b-a3b-4bit",
+        "status": "error",
+        "error": "server restarted mid-run",
+        "seconds": 0,
+        "cost": null,
+        "started_at": null,
+        "finished_at": null,
+        "queued_at": "2026-09-28T00:55:54.838Z",
+        "resumes": 1
+      },
+      {
+        "model": "exo__minimax-m2-1-8bit",
+        "status": "error",
+        "error": "server restarted mid-run",
+        "seconds": 0,
+        "cost": null,
+        "started_at": null,
+        "finished_at": null,
+        "queued_at": "2026-09-28T00:55:54.866Z",
+        "resumes": 1
+      }
+    ],
+    "aiPick": null
+  },
+  {
+    "id": "98cfc5a1ebdc",
+    "title": "History Competition #41 — An Empire That Breathes",
+    "prompt": "Build this as one complete, self-contained HTML file: An INVENTED empire that breathes across a map as you drag a century slider — borders bloom and recede, cities rise as glowing dots, and event notes fade in at the turning points, with a legend. 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": "History",
+    "designTools": false,
+    "created_at": "2026-09-28T01:15:20.351Z",
+    "winner": null,
+    "runs": [
+      {
+        "model": "exo__gemma-4-e2b-it-6bit",
+        "status": "error",
+        "error": "timeout after 300s",
+        "seconds": 300,
+        "cost": null,
+        "started_at": "2026-09-28T01:15:21.032Z",
+        "finished_at": "2026-09-28T01:20:21.394Z",
+        "queued_at": "2026-09-28T01:15:20.503Z",
+        "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3-30B-A3B-Instruct-2507-4bit)"
+      },
+      {
+        "model": "exo__qwen3-5-27b-8bit",
+        "status": "error",
+        "error": "timeout after 300s",
+        "seconds": 300,
+        "cost": null,
+        "started_at": "2026-09-28T01:20:21.469Z",
+        "finished_at": "2026-09-28T01:25:21.827Z",
+        "queued_at": "2026-09-28T01:15:20.591Z",
+        "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3-30B-A3B-Instruct-2507-4bit)"
+      },
+      {
+        "model": "exo__kimi-k2-thinking",
+        "status": "running",
+        "error": null,
+        "seconds": null,
+        "cost": null,
+        "started_at": "2026-09-28T01:25:21.885Z",
+        "finished_at": null,
+        "queued_at": "2026-09-28T01:15:20.648Z",
+        "fellBack": "http://127.0.0.1:8000 (mlx-community/Qwen3-30B-A3B-Instruct-2507-4bit)"
+      },
+      {
+        "model": "exo__qwen3-coder-next-bf16",
         "status": "queued",
         "error": null,
         "seconds": null,
         "cost": null,
         "started_at": null,
         "finished_at": null,
-        "queued_at": "2026-09-28T00:55:54.807Z"
+        "queued_at": "2026-09-28T01:15:20.734Z"
       },
       {
-        "model": "exo__qwen3-5-35b-a3b-4bit",
+        "model": "exo__deepseek-v3-2-4bit",
         "status": "queued",
         "error": null,
         "seconds": null,
         "cost": null,
         "started_at": null,
         "finished_at": null,
-        "queued_at": "2026-09-28T00:55:54.838Z"
+        "queued_at": "2026-09-28T01:15:20.866Z"
       },
       {
-        "model": "exo__minimax-m2-1-8bit",
+        "model": "exo__nvidia-nemotron-nano-9b-v2-6bit",
         "status": "queued",
         "error": null,
         "seconds": null,
         "cost": null,
         "started_at": null,
         "finished_at": null,
-        "queued_at": "2026-09-28T00:55:54.866Z"
+        "queued_at": "2026-09-28T01:15:20.962Z"
       }
     ]
   }
diff --git a/yolo/arena-loop-state.json b/yolo/arena-loop-state.json
index 588f787..d732518 100644
--- a/yolo/arena-loop-state.json
+++ b/yolo/arena-loop-state.json
@@ -1 +1 @@
-{"promptIdx":3,"modelOffset":100,"compCount":{"Art":82,"Culture":81,"News":81,"Political Cartoon":81,"Games":41,"Real Work":41,"Data Viz":41,"Science":41,"Music":41,"Sports":41,"History":40,"Nature & Space":40,"Comedy":40,"Demoscene":40,"Finance":40,"Design":40},"catIdx":10,"perCat":{"Art":1,"Culture":1,"News":1,"Political Cartoon":1,"Games":2,"Real Work":2,"Data Viz":2,"Science":2,"Music":2,"Sports":2,"History":1,"Nature & Space":1,"Comedy":1,"Demoscene":1,"Finance":1,"Design":1}}
\ No newline at end of file
+{"promptIdx":3,"modelOffset":106,"compCount":{"Art":82,"Culture":81,"News":81,"Political Cartoon":81,"Games":41,"Real Work":41,"Data Viz":41,"Science":41,"Music":41,"Sports":41,"History":41,"Nature & Space":40,"Comedy":40,"Demoscene":40,"Finance":40,"Design":40},"catIdx":11,"perCat":{"Art":1,"Culture":1,"News":1,"Political Cartoon":1,"Games":2,"Real Work":2,"Data Viz":2,"Science":2,"Music":2,"Sports":2,"History":2,"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 8c56076..346129c 100644
--- a/yolo/daily-log.jsonl
+++ b/yolo/daily-log.jsonl
@@ -905,3 +905,4 @@
 {"ts":"2026-09-27T23:10:38.823Z","id":"cbaf068e0f6a","promptId":"flow-infographic","category":"Data Viz","title":"Data Viz Competition #41 — Bean-to-Cup Sankey","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}
 {"ts":"2026-09-28T00:00:45.785Z","id":"1930befe0c60","promptId":"pendulum","category":"Science","title":"Science Competition #41 — The Painting Pendulum","models":6,"done":0,"errored":0,"settled":false,"aiPick":null,"loop":true}
 {"ts":"2026-09-28T00:50:54.523Z","id":"05e5fa452757","promptId":"synth","category":"Music","title":"Music Competition #41 — The Singing Creature Synth","models":6,"done":0,"errored":0,"settled":false,"aiPick":null,"loop":true}
+{"ts":"2026-09-28T01:10:19.976Z","id":"57d8f565079d","promptId":"bracket","category":"Sports","title":"Sports Competition #41 — Mascot Clash Bracket","models":6,"done":0,"errored":6,"settled":true,"aiPick":null,"loop":true}

← e9898ef auto-data-snapshot: 2026-09-27T17:55:26 (3 data files) — dat  ·  back to Model Arena  ·  auto-data-snapshot: 2026-09-27T18:56:55 (3 data files) — dat 5b54efa →