[object Object]

← back to Model Arena

auto-save: 2026-07-22T23:17:18 (4 files) — data/challenges.json data/costlog.jsonl data/votes.jsonl data/artifacts/02bc35a3d0b2/

39b20bdd7a4f138a6eae647956964ced08cbed27 · 2026-07-22 23:17:24 -0700 · Steve Abrams

Files touched

Diff

commit 39b20bdd7a4f138a6eae647956964ced08cbed27
Author: Steve Abrams <steve@designerwallcoverings.com>
Date:   Wed Jul 22 23:17:24 2026 -0700

    auto-save: 2026-07-22T23:17:18 (4 files) — data/challenges.json data/costlog.jsonl data/votes.jsonl data/artifacts/02bc35a3d0b2/
---
 data/artifacts/02bc35a3d0b2/gemma3-12b.html | 10 ++++
 data/artifacts/02bc35a3d0b2/gpt.html        | 15 ++++++
 data/artifacts/02bc35a3d0b2/grok.html       | 13 +++++
 data/artifacts/02bc35a3d0b2/hermes3-8b.html | 15 ++++++
 data/artifacts/02bc35a3d0b2/kimi.html       | 13 +++++
 data/artifacts/02bc35a3d0b2/qwen25-7b.html  |  1 +
 data/artifacts/02bc35a3d0b2/qwen3-14b.html  |  2 +
 data/challenges.json                        | 80 +++++++++++++++++++++++++++++
 data/costlog.jsonl                          |  3 ++
 data/votes.jsonl                            |  1 +
 10 files changed, 153 insertions(+)

diff --git a/data/artifacts/02bc35a3d0b2/gemma3-12b.html b/data/artifacts/02bc35a3d0b2/gemma3-12b.html
new file mode 100644
index 0000000..273401d
--- /dev/null
+++ b/data/artifacts/02bc35a3d0b2/gemma3-12b.html
@@ -0,0 +1,10 @@
+<!DOCTYPE html>
+<html>
+<head>
+<title>Color Response</title>
+<style> body { font-family: sans-serif; } </style>
+</head>
+<body>
+<script>document.body.innerText = "Blue";</script>
+</body>
+</html>
\ No newline at end of file
diff --git a/data/artifacts/02bc35a3d0b2/gpt.html b/data/artifacts/02bc35a3d0b2/gpt.html
new file mode 100644
index 0000000..0fb87b2
--- /dev/null
+++ b/data/artifacts/02bc35a3d0b2/gpt.html
@@ -0,0 +1,15 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+<meta charset="UTF-8">
+<title>Color</title>
+<style>
+  body{margin:0;display:flex;align-items:center;justify-content:center;height:100vh;font-family:Arial,Helvetica,sans-serif;font-size:24px}
+</style>
+</head>
+<body>
+<script>
+  document.body.textContent = "Blue.";
+</script>
+</body>
+</html>
\ No newline at end of file
diff --git a/data/artifacts/02bc35a3d0b2/grok.html b/data/artifacts/02bc35a3d0b2/grok.html
new file mode 100644
index 0000000..b9778c6
--- /dev/null
+++ b/data/artifacts/02bc35a3d0b2/grok.html
@@ -0,0 +1,13 @@
+<!DOCTYPE html>
+<html>
+<head>
+<meta charset="UTF-8">
+<style>
+body{margin:0;height:100vh;display:flex;align-items:center;justify-content:center;font-family:system-ui,sans-serif;background:#f0f0f0;color:#333}
+p{font-size:1.5rem;margin:0}
+</style>
+</head>
+<body>
+<p>The ocean is blue.</p>
+</body>
+</html>
\ No newline at end of file
diff --git a/data/artifacts/02bc35a3d0b2/hermes3-8b.html b/data/artifacts/02bc35a3d0b2/hermes3-8b.html
new file mode 100644
index 0000000..2802c62
--- /dev/null
+++ b/data/artifacts/02bc35a3d0b2/hermes3-8b.html
@@ -0,0 +1,15 @@
+<!DOCTYPE html>
+<html>
+<head>
+<title>Color</title>
+<style>
+body { background-color: #00ff00; }
+h1 { color: #00ff00; text-align: center; margin-top: 100px; font-size: 48px; }
+</style>
+</head>
+<body>
+<h1>Lime</h1>
+<script>
+</script>
+</body>
+</html>
\ No newline at end of file
diff --git a/data/artifacts/02bc35a3d0b2/kimi.html b/data/artifacts/02bc35a3d0b2/kimi.html
new file mode 100644
index 0000000..ed11db9
--- /dev/null
+++ b/data/artifacts/02bc35a3d0b2/kimi.html
@@ -0,0 +1,13 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+<meta charset="UTF-8">
+<style>
+body{font-family:sans-serif;display:flex;justify-content:center;align-items:center;height:100vh;margin:0}
+</style>
+</head>
+<body>
+Violet is a purple color.
+<script>console.log('done')</script>
+</body>
+</html>
\ No newline at end of file
diff --git a/data/artifacts/02bc35a3d0b2/qwen25-7b.html b/data/artifacts/02bc35a3d0b2/qwen25-7b.html
new file mode 100644
index 0000000..5057f7a
--- /dev/null
+++ b/data/artifacts/02bc35a3d0b2/qwen25-7b.html
@@ -0,0 +1 @@
+<!DOCTYPE html><html><head><style></style></head><body contenteditable>"red"</body></html>
\ No newline at end of file
diff --git a/data/artifacts/02bc35a3d0b2/qwen3-14b.html b/data/artifacts/02bc35a3d0b2/qwen3-14b.html
new file mode 100644
index 0000000..d653379
--- /dev/null
+++ b/data/artifacts/02bc35a3d0b2/qwen3-14b.html
@@ -0,0 +1,2 @@
+<!DOCTYPE html>
+<html lang="en"><head><meta charset="UTF-8"><title>Color</title><style>body{font-family:sans-serif;text-align:center;margin-top:20%;color:#2e8b57}p{font-size:2em}</style></head><body><p>The color is turquoise.</p><script></script></body></html>
\ No newline at end of file
diff --git a/data/challenges.json b/data/challenges.json
index 539ee7c..b49c81b 100644
--- a/data/challenges.json
+++ b/data/challenges.json
@@ -537,5 +537,85 @@
         "cost": null
       }
     ]
+  },
+  {
+    "id": "02bc35a3d0b2",
+    "title": "Propagation all-7",
+    "prompt": "Reply with exactly one short sentence naming a color.",
+    "created_at": "2026-07-23T06:11:00.871Z",
+    "winner": "grok",
+    "runs": [
+      {
+        "model": "qwen3-14b",
+        "status": "done",
+        "error": null,
+        "seconds": 19,
+        "cost": 0,
+        "started_at": "2026-07-23T06:11:00.874Z",
+        "finished_at": "2026-07-23T06:11:19.427Z",
+        "bytes": 260
+      },
+      {
+        "model": "gemma3-12b",
+        "status": "done",
+        "error": null,
+        "seconds": 6,
+        "cost": 0,
+        "started_at": "2026-07-23T06:11:19.427Z",
+        "finished_at": "2026-07-23T06:11:25.488Z",
+        "bytes": 192
+      },
+      {
+        "model": "hermes3-8b",
+        "status": "done",
+        "error": null,
+        "seconds": 3,
+        "cost": 0,
+        "started_at": "2026-07-23T06:11:25.488Z",
+        "finished_at": "2026-07-23T06:11:28.567Z",
+        "bytes": 246
+      },
+      {
+        "model": "qwen25-7b",
+        "status": "done",
+        "error": null,
+        "seconds": 4,
+        "cost": 0,
+        "started_at": "2026-07-23T06:11:28.568Z",
+        "finished_at": "2026-07-23T06:11:32.160Z",
+        "bytes": 90
+      },
+      {
+        "model": "kimi",
+        "status": "done",
+        "error": null,
+        "seconds": 60,
+        "cost": 0.0056,
+        "started_at": "2026-07-23T06:11:00.875Z",
+        "finished_at": "2026-07-23T06:12:00.482Z",
+        "bytes": 279
+      },
+      {
+        "model": "gpt",
+        "status": "done",
+        "error": null,
+        "seconds": 2,
+        "cost": 0.0015,
+        "started_at": "2026-07-23T06:11:00.875Z",
+        "finished_at": "2026-07-23T06:11:03.116Z",
+        "bytes": 328
+      },
+      {
+        "model": "grok",
+        "status": "done",
+        "error": null,
+        "seconds": 5,
+        "cost": 0.0025,
+        "started_at": "2026-07-23T06:11:00.876Z",
+        "finished_at": "2026-07-23T06:11:05.377Z",
+        "bytes": 301
+      }
+    ],
+    "voted_at": "2026-07-23T06:13:14.106Z"
   }
 ]
\ No newline at end of file
diff --git a/data/costlog.jsonl b/data/costlog.jsonl
index ed466ee..d3e4927 100644
--- a/data/costlog.jsonl
+++ b/data/costlog.jsonl
@@ -6,3 +6,6 @@
 {"ts":"2026-07-23T06:06:18.884Z","provider":"openai","model":"gpt-5.1","task":"model-arena","input_tokens":103,"output_tokens":49,"cost_usd":0.000866}
 {"ts":"2026-07-23T06:06:19.831Z","provider":"xai","model":"grok-4.5","task":"model-arena","input_tokens":308,"output_tokens":33,"cost_usd":0.001419}
 {"ts":"2026-07-23T06:06:46.529Z","provider":"moonshot","model":"kimi-k2.5","task":"model-arena","input_tokens":104,"output_tokens":1221,"cost_usd":0.003115}
+{"ts":"2026-07-23T06:11:03.114Z","provider":"openai","model":"gpt-5.1","task":"model-arena","input_tokens":91,"output_tokens":99,"cost_usd":0.001545}
+{"ts":"2026-07-23T06:11:05.377Z","provider":"xai","model":"grok-4.5","task":"model-arena","input_tokens":295,"output_tokens":108,"cost_usd":0.002505}
+{"ts":"2026-07-23T06:12:00.481Z","provider":"moonshot","model":"kimi-k2.5","task":"model-arena","input_tokens":92,"output_tokens":2223,"cost_usd":0.005613}
diff --git a/data/votes.jsonl b/data/votes.jsonl
index 6081896..777b2ab 100644
--- a/data/votes.jsonl
+++ b/data/votes.jsonl
@@ -2,3 +2,4 @@
 {"ts":"2026-07-23T05:51:00.009Z","challenge":"0ac1af2eaed4","title":"Smoke Test: Particle Fireworks","winner":"kimi","field":["hermes3-8b","gemma3-12b","qwen3-14b","kimi"]}
 {"ts":"2026-07-23T05:51:21.751Z","challenge":"966d54f224fd","title":"neon city","winner":"grok","field":["gemma3-12b","hermes3-8b","kimi","grok"]}
 {"ts":"2026-07-23T05:51:45.195Z","challenge":"74df3b61e7ca","title":"Synthwave Visualizer","winner":"grok","field":["gemma3-12b","hermes3-8b","kimi","grok"]}
+{"ts":"2026-07-23T06:13:14.106Z","challenge":"02bc35a3d0b2","title":"Propagation all-7","winner":"grok","field":["qwen3-14b","gemma3-12b","hermes3-8b","qwen25-7b","kimi","gpt","grok"]}

← a7941bb liveness: fix OpenAI max_completion_tokens (gpt-5.1 generate  ·  back to Model Arena  ·  mac1: revive Ollama (unstuck pinned qwen3:14b); restore aren 84ddac1 →