sqlite/sqlite

Official Git mirror of the SQLite source tree

9,434 c
13,514
Generated Behavioral Tests
67.0%
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 4.7 Anthropic 67.0% $1.08 37
2 Claude Haiku 4.5 Anthropic 20.3% $0.57 137
3 GPT 5 mini OpenAI 19.9% $0.01 14
4 Claude Sonnet 4.6 Anthropic 1.3% $28.86 573
5 Gemini 3 Flash Google 0.9% $0.19 74
6 GPT 5.4 OpenAI 0.6% $0.20 9
7 GPT 5.4 mini OpenAI 0.5% $0.02 11
8 Gemini 3.1 Pro Google 0.4% $0.85 77
9 Claude Opus 4.6 Anthropic 0.0% $4.54 274

Click row to see model details