← back to Model Arena
auto-data-snapshot: 2026-09-08T15:35:04 (2 data files) — data/challenges.json data/costlog.jsonl
50a549a989c545279b0d08fca29a104af87ada8b · 2026-09-08 15:39:35 -0700 · auto-commit-fleet
Files touched
M data/challenges.jsonM data/costlog.jsonl
Diff
commit 50a549a989c545279b0d08fca29a104af87ada8b
Author: auto-commit-fleet <steve@designerwallcoverings.com>
Date: Tue Sep 8 15:39:35 2026 -0700
auto-data-snapshot: 2026-09-08T15:35:04 (2 data files) — data/challenges.json data/costlog.jsonl
---
data/challenges.json | 166 +++++++++++++++++++++++++++++++++++++++++++++++++++
data/costlog.jsonl | 1 +
2 files changed, 167 insertions(+)
diff --git a/data/challenges.json b/data/challenges.json
index 5994933..baa62a8 100644
--- a/data/challenges.json
+++ b/data/challenges.json
@@ -36318,5 +36318,171 @@
"judging": false,
"aiPick": null,
"judged_at": "2026-09-08T14:15:57.200Z"
+ },
+ {
+ "id": "e5ca87e59211",
+ "title": "Wild Orbs — Asteroids where shooting orbs does wild things",
+ "prompt": "Build a complete, polished single-file HTML5 Canvas game: an Asteroids-style game where the asteroids are replaced by ORBS, and EACH orb does something WILD and different when you shoot it. Include at least 8 visually distinct wild orb types, each with a clearly different on-hit behavior — e.g. splits into a homing swarm; explodes into a gravity well that sucks in your bullets and ship; phases/teleports when hit; spawns a black hole; reverses your controls for a few seconds; shatters into ricocheting shards; drops a time-slow bubble; chain-reaction color bomb that detonates nearby orbs; mirror-clones itself; rubber-band bounces off walls faster each hit. Ship: thrust + inertia + rotation + screen-wrap + fire, with a cooldown. Add particle effects, bullet trails, screen shake on big hits, glow/gradients, escalating waves, score, lives, a start screen and a game-over screen. Sound via WebAudio (thrust, shoot, orb-specific hit sounds). Controls: arrows/WASD to fly, space to shoot. Return ONE self-contained HTML file, no external assets or CDNs. Be very detailed and make it juicy.",
+ "category": "Games",
+ "designTools": false,
+ "created_at": "2026-09-08T22:15:36.141Z",
+ "winner": null,
+ "runs": [
+ {
+ "model": "qwen3-14b",
+ "status": "done",
+ "error": null,
+ "seconds": 108,
+ "cost": 0,
+ "started_at": "2026-09-08T22:15:36.221Z",
+ "finished_at": "2026-09-08T22:17:23.833Z",
+ "queued_at": "2026-09-08T22:15:36.149Z",
+ "bytes": 17069,
+ "thumb": true,
+ "aiScore": null,
+ "aiReason": "judge failed: all vision panelists failed"
+ },
+ {
+ "model": "gemma3-12b",
+ "status": "error",
+ "error": "ollama bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-08T22:17:23.840Z",
+ "finished_at": "2026-09-08T22:17:23.849Z",
+ "queued_at": "2026-09-08T22:15:36.154Z"
+ },
+ {
+ "model": "hermes3-8b",
+ "status": "error",
+ "error": "ollama bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-08T22:17:23.854Z",
+ "finished_at": "2026-09-08T22:17:23.861Z",
+ "queued_at": "2026-09-08T22:15:36.159Z"
+ },
+ {
+ "model": "qwen25-7b",
+ "status": "error",
+ "error": "ollama bad response: 503",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-08T22:15:36.232Z",
+ "finished_at": "2026-09-08T22:15:36.466Z",
+ "queued_at": "2026-09-08T22:15:36.164Z"
+ },
+ {
+ "model": "hf-qwen-coder-32b",
+ "status": "error",
+ "error": "ollama bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-08T22:17:23.866Z",
+ "finished_at": "2026-09-08T22:17:23.873Z",
+ "queued_at": "2026-09-08T22:15:36.169Z"
+ },
+ {
+ "model": "muse",
+ "status": "error",
+ "error": "ollama bad response: 404",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-08T22:17:23.879Z",
+ "finished_at": "2026-09-08T22:17:23.885Z",
+ "queued_at": "2026-09-08T22:15:36.174Z"
+ },
+ {
+ "model": "claude-code",
+ "status": "done",
+ "error": null,
+ "seconds": 364,
+ "cost": 0,
+ "started_at": "2026-09-08T22:15:36.238Z",
+ "finished_at": "2026-09-08T22:21:40.626Z",
+ "queued_at": "2026-09-08T22:15:36.179Z",
+ "bytes": 67797,
+ "thumb": true,
+ "aiScore": null,
+ "aiReason": "judge failed: all vision panelists failed"
+ },
+ {
+ "model": "kimi",
+ "status": "error",
+ "error": "MOONSHOT_API_KEY not set — metered model unavailable",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-08T22:15:36.244Z",
+ "finished_at": "2026-09-08T22:15:36.287Z",
+ "queued_at": "2026-09-08T22:15:36.183Z"
+ },
+ {
+ "model": "gpt",
+ "status": "error",
+ "error": "openai error: {\"message\":\"Your project has reached its configured enforced spend limit. Update your limit at https://platform.openai.com/settings/proj_scd7OpeOGvI3w9ccmOmBvcPO/limits.\",\"type\":\"insufficient_quota\",\"",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-08T22:15:36.249Z",
+ "finished_at": "2026-09-08T22:15:36.568Z",
+ "queued_at": "2026-09-08T22:15:36.188Z"
+ },
+ {
+ "model": "codex",
+ "status": "error",
+ "error": "openai responses error: {\"message\":\"Your project has reached its configured enforced spend limit. Update your limit at https://platform.openai.com/settings/proj_scd7OpeOGvI3w9ccmOmBvcPO/limits.\",\"type\":\"insufficient_quota\",\"",
+ "seconds": 1,
+ "cost": null,
+ "started_at": "2026-09-08T22:15:36.261Z",
+ "finished_at": "2026-09-08T22:15:36.919Z",
+ "queued_at": "2026-09-08T22:15:36.193Z"
+ },
+ {
+ "model": "grok",
+ "status": "error",
+ "error": "XAI_API_KEY not set — metered model unavailable",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-08T22:15:36.267Z",
+ "finished_at": "2026-09-08T22:15:36.292Z",
+ "queued_at": "2026-09-08T22:15:36.198Z"
+ },
+ {
+ "model": "deepseek-v3",
+ "status": "error",
+ "error": "openrouter error: {\"message\":\"Provider returned error\",\"code\":429,\"metadata\":{\"raw\":\"deepseek/deepseek-chat is temporarily rate-limited upstream. Please retry shortly, or add your own key to accumulate your rate limits",
+ "seconds": 1,
+ "cost": 0.0056,
+ "started_at": "2026-09-08T22:38:26.103Z",
+ "finished_at": "2026-09-08T22:38:27.350Z",
+ "queued_at": "2026-09-08T22:38:26.096Z",
+ "bytes": 9900,
+ "thumb": true,
+ "aiScore": null,
+ "aiReason": "judge failed: all vision panelists failed"
+ },
+ {
+ "model": "deepseek-r1",
+ "status": "error",
+ "error": "openrouter error: {\"message\":\"This request requires more credits, or fewer max_tokens. You requested up to 16000 tokens, but can only afford 15991. To increase, visit https://openrouter.ai/settings/credits and upgrade ",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-08T22:15:36.277Z",
+ "finished_at": "2026-09-08T22:15:36.405Z",
+ "queued_at": "2026-09-08T22:15:36.208Z"
+ },
+ {
+ "model": "astra",
+ "status": "error",
+ "error": "openrouter error: {\"message\":\"This request requires more credits, or fewer max_tokens. You requested up to 16000 tokens, but can only afford 726. To increase, visit https://openrouter.ai/settings/credits and upgrade to",
+ "seconds": 0,
+ "cost": null,
+ "started_at": "2026-09-08T22:15:36.282Z",
+ "finished_at": "2026-09-08T22:15:36.383Z",
+ "queued_at": "2026-09-08T22:15:36.213Z"
+ }
+ ],
+ "judging": false,
+ "aiPick": null,
+ "judged_at": "2026-09-08T22:21:43.162Z"
}
]
\ No newline at end of file
diff --git a/data/costlog.jsonl b/data/costlog.jsonl
index e5482bf..07b8012 100644
--- a/data/costlog.jsonl
+++ b/data/costlog.jsonl
@@ -418,3 +418,4 @@
{"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}
+{"ts":"2026-09-08T22:17:32.834Z","provider":"openrouter","model":"deepseek/deepseek-chat","task":"model-arena","input_tokens":334,"output_tokens":2728,"cost_usd":0.005623}
← cd49868 add OpenAI Astra 6.0 (gpt-6-astra) to model-arena via OpenRo
·
back to Model Arena
·
auto-data-snapshot: 2026-09-08T16:14:09 (1 data files) — dat 9c460ec →