AygeaandClaude
2f99dd1e35
7 entries (30→37 total). Muse Glimmer 28B (GGUF) avg 80.7 — the strongest model in the benchmark, 6/7 prompts Minor Logic Flaws: lfu 76 | webhook 81 | automation 89 | rust 85 | data 88 | tts 58 | mcp 88 Standout results: - rust 85 (KAT 36, Qwen3-Coder 54) — real tokio channels (mpsc::channel, not hallucinated mpsc::bounded), two-tier CancellationToken, zero clippy lints; one-line E0507 compile fix. - automation 89 — first model to print a correct summary (98/2/0/100); atomic temp+fsync+rename checkpointing. - data 88 edges out Gemma-26B's 86; mcp 88 sets the bar on a new prompt. Only weak spot: tts 58 (backpressure raises instead of awaits, like Qwen3-Coder). Captured via the native /api/v1/chat fix (real tok/sec + TTFT). Slow deep-thinker: ~17-19 t/s, 5-9 min/prompt, ~5-9k tokens incl. reasoning. Also gitignore checkpoint.json (automation test runtime artifact). Co-Authored-By: Claude <noreply@anthropic.com>
26 lines
674 B
Plaintext
26 lines
674 B
Plaintext
# --- Generated / build artifacts ---
|
|
# Dashboard HTML is generated by generate_dashboard.py from data/benchmark_history.json.
|
|
# Keep them OUT of git so the repo only holds source — the site regenerates on deploy.
|
|
# (If you'd rather commit the built HTML instead, comment out these lines.)
|
|
/dashboard.html
|
|
/pages/
|
|
# /data/benchmark_history.json # <-- uncomment to keep history local-only too
|
|
|
|
# --- Scratch / previews / tooling ---
|
|
*.png
|
|
/playwright-mcp/
|
|
/.playwright-mcp/
|
|
__pycache__/
|
|
*.pyc
|
|
.DS_Store
|
|
|
|
# --- Local env ---
|
|
.env
|
|
.env.*
|
|
*.local
|
|
|
|
# --- Webhook secret (NEVER commit) ---
|
|
.webhook.secret
|
|
# automation prompt test artifact (runtime-generated)
|
|
checkpoint.json
|