rochacbruno/marmite

Markdown makes sites - A Static Site Generator for Blogs

837 rs medium
668
Generated Behavioral Tests
45.4%
Best Score
# Model Score help_outline Percentage of hidden behavioral tests passed. Cost help_outline Total API cost in USD for this task instance. Calls help_outline Number of LLM API calls for this task instance.
1 Claude Opus 4.6 Anthropic 45.4% $13.96 206
2 GPT 5 mini OpenAI 27.8% $0.02 13
3 GPT 5.4 OpenAI 22.5% $0.33 11
4 Gemini 3.1 Pro Google 22.3% $1.26 62
5 Claude Opus 4.7 Anthropic 21.4% $0.74 28
6 Gemini 3 Flash Google 18.6% $0.35 79
7 Claude Sonnet 4.6 Anthropic 11.2% $57.18 790
8 GPT 5.4 mini OpenAI 8.2% $0.06 14
9 Claude Haiku 4.5 Anthropic 0.0% $0.94 115

Click row to see model details