← back to Model Arena
auto-data-snapshot: 2026-08-31T12:34:16 (6 data files) — data/artifacts/5ed25e8a4aae/claude-code.png data/artifacts/5ed25e8a4aae/codex.png data/artifacts/5ed25e8a4aae/qwen25-7b.png data/artifacts/5ed25e8a4aae/qwen3-14b.png data/challenges.json
716ee05e4024e2ba548d96b0709cf32ae1298338 · 2026-08-31 12:38:29 -0700 · auto-commit-fleet
Files touched
A data/artifacts/5ed25e8a4aae/claude-code.pngA data/artifacts/5ed25e8a4aae/codex.pngA data/artifacts/5ed25e8a4aae/qwen25-7b.pngA data/artifacts/5ed25e8a4aae/qwen3-14b.pngM data/challenges.jsonM data/costlog.jsonl
Diff
commit 716ee05e4024e2ba548d96b0709cf32ae1298338
Author: auto-commit-fleet <steve@designerwallcoverings.com>
Date: Mon Aug 31 12:38:29 2026 -0700
auto-data-snapshot: 2026-08-31T12:34:16 (6 data files) — data/artifacts/5ed25e8a4aae/claude-code.png data/artifacts/5ed25e8a4aae/codex.png data/artifacts/5ed25e8a4aae/qwen25-7b.png data/artifacts/5ed25e8a4aae/qwen3-14b.png data/challenges.json
---
data/artifacts/5ed25e8a4aae/claude-code.png | Bin 0 -> 240017 bytes
data/artifacts/5ed25e8a4aae/codex.png | Bin 0 -> 201194 bytes
data/artifacts/5ed25e8a4aae/qwen25-7b.png | Bin 0 -> 20129 bytes
data/artifacts/5ed25e8a4aae/qwen3-14b.png | Bin 0 -> 127037 bytes
data/challenges.json | 90 ++++++++++++++++++++++++++++
data/costlog.jsonl | 1 +
6 files changed, 91 insertions(+)
diff --git a/data/artifacts/5ed25e8a4aae/claude-code.png b/data/artifacts/5ed25e8a4aae/claude-code.png
new file mode 100644
index 0000000..9d64319
Binary files /dev/null and b/data/artifacts/5ed25e8a4aae/claude-code.png differ
diff --git a/data/artifacts/5ed25e8a4aae/codex.png b/data/artifacts/5ed25e8a4aae/codex.png
new file mode 100644
index 0000000..9514ce8
Binary files /dev/null and b/data/artifacts/5ed25e8a4aae/codex.png differ
diff --git a/data/artifacts/5ed25e8a4aae/qwen25-7b.png b/data/artifacts/5ed25e8a4aae/qwen25-7b.png
new file mode 100644
index 0000000..ac2c651
Binary files /dev/null and b/data/artifacts/5ed25e8a4aae/qwen25-7b.png differ
diff --git a/data/artifacts/5ed25e8a4aae/qwen3-14b.png b/data/artifacts/5ed25e8a4aae/qwen3-14b.png
new file mode 100644
index 0000000..faf9b0f
Binary files /dev/null and b/data/artifacts/5ed25e8a4aae/qwen3-14b.png differ
diff --git a/data/challenges.json b/data/challenges.json
index a83a4dc..3e34a95 100644
--- a/data/challenges.json
+++ b/data/challenges.json
@@ -33527,5 +33527,95 @@
"judging": false,
"aiPick": "qwen3-14b",
"judged_at": "2026-08-31T14:15:41.306Z"
+ },
+ {
+ "id": "5ed25e8a4aae",
+ "title": "Neon City Driving",
+ "prompt": "Build a game that uses baguettes in paris to fight each other",
+ "category": "Games",
+ "designTools": true,
+ "created_at": "2026-08-31T19:32:03.651Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "qwen3-14b",
+ "status": "done",
+ "error": null,
+ "seconds": 36,
+ "cost": 0,
+ "started_at": "2026-08-31T19:32:03.675Z",
+ "finished_at": "2026-08-31T19:32:40.095Z",
+ "queued_at": "2026-08-31T19:32:03.657Z",
+ "bytes": 5666,
+ "thumb": true,
+ "aiScore": 6.5,
+ "aiReason": "The game concept is clear and visually appealing but lacks additional features or depth.",
+ "aiScores": {
+ "qwen2.5vl:7b": 7,
+ "minicpm-v:latest": 6
+ },
+ "aiSpread": 1
+ },
+ {
+ "model": "qwen25-7b",
+ "status": "done",
+ "error": null,
+ "seconds": 18,
+ "cost": 0,
+ "started_at": "2026-08-31T19:32:03.680Z",
+ "finished_at": "2026-08-31T19:32:21.583Z",
+ "queued_at": "2026-08-31T19:32:03.662Z",
+ "bytes": 1575,
+ "thumb": true,
+ "aiScore": 6.8,
+ "aiReason": "The game concept is clear and the visual design is simple but effective.",
+ "aiScores": {
+ "qwen2.5vl:7b": 7,
+ "minicpm-v:latest": 6.5
+ },
+ "aiSpread": 0.5
+ },
+ {
+ "model": "claude-code",
+ "status": "done",
+ "error": null,
+ "seconds": 221,
+ "cost": 0,
+ "started_at": "2026-08-31T19:32:03.684Z",
+ "finished_at": "2026-08-31T19:35:44.351Z",
+ "queued_at": "2026-08-31T19:32:03.666Z",
+ "bytes": 28946,
+ "thumb": true,
+ "aiScore": 7.5,
+ "aiReason": "The game concept is clear and visually appealing, effectively capturing the essence of a baguette duel in Paris.",
+ "aiScores": {
+ "qwen2.5vl:7b": 9,
+ "minicpm-v:latest": 6
+ },
+ "aiSpread": 3
+ },
+ {
+ "model": "codex",
+ "status": "done",
+ "error": null,
+ "seconds": 22,
+ "cost": 0.0477,
+ "started_at": "2026-08-31T19:32:03.690Z",
+ "finished_at": "2026-08-31T19:32:26.083Z",
+ "queued_at": "2026-08-31T19:32:03.671Z",
+ "bytes": 10916,
+ "thumb": true,
+ "aiScore": 7.5,
+ "aiReason": "The game concept is clear and visually appealing, effectively representing the challenge of a baguette duel in Paris.",
+ "aiScores": {
+ "qwen2.5vl:7b": 9,
+ "minicpm-v:latest": 6
+ },
+ "aiSpread": 3
+ }
+ ],
+ "judging": false,
+ "aiPick": "claude-code",
+ "judged_at": "2026-08-31T19:36:14.308Z"
}
]
\ No newline at end of file
diff --git a/data/costlog.jsonl b/data/costlog.jsonl
index 4f37e2a..e5482bf 100644
--- a/data/costlog.jsonl
+++ b/data/costlog.jsonl
@@ -417,3 +417,4 @@
{"ts":"2026-07-25T15:26:53.953Z","provider":"openai","model":"gpt-5.1","task":"model-arena-tools","input_tokens":3514,"output_tokens":9983,"cost_usd":0.145911}
{"ts":"2026-07-25T15:27:14.625Z","provider":"xai","model":"grok-4.5","task":"model-arena-tools","input_tokens":4070,"output_tokens":8308,"cost_usd":0.13683}
{"ts":"2026-07-25T15:27:35.786Z","provider":"moonshot","model":"kimi-k2.5","task":"model-arena-tools","input_tokens":6148,"output_tokens":6329,"cost_usd":0.019511}
+{"ts":"2026-08-31T19:32:26.082Z","provider":"openai","model":"gpt-5.3-codex","task":"model-arena","input_tokens":611,"output_tokens":3332,"cost_usd":0.047717}
← 7006d6b redesign Model Arena as a professional workspace
·
back to Model Arena
·
snapshot generated arena artifacts before UI verification 9152be0 →