multiprocessio/dsq

Commandline tool for running SQL queries against JSON, CSV, Excel, Parquet, and more.

3,867 go easy
542
Generated Behavioral Tests
80.3%
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 Sonnet 4.6 Anthropic 80.3% $32.92 610
2 Claude Opus 4.6 Anthropic 76.4% $14.97 351
3 Claude Opus 4.7 Anthropic 65.9% $3.28 98
4 Gemini 3.1 Pro Google 50.6% $1.64 100
5 GPT 5.4 OpenAI 49.3% $0.54 24
6 Claude Haiku 4.5 Anthropic 30.3% $0.77 134
7 GPT 5 mini OpenAI 25.3% $0.04 27
8 GPT 5.4 mini OpenAI 10.1% $0.03 8
9 Gemini 3 Flash Google 0.0% $0.38 118

Click row to see model details