ggreer/the_silver_searcher
A code-searching tool similar to ack, but faster.
Results by Model
| # | Model | Score Percentage of hidden behavioral tests passed. | Cost Total API cost in USD for this task instance. | Calls Number of LLM API calls for this task instance. | |
|---|---|---|---|---|---|
| 1 |  |
Claude Sonnet 4.6 Anthropic | 59.3% | $13.76 | 443 |
| 2 | |
Claude Opus 4.6 Anthropic | 48.0% | $7.38 | 195 |
| 3 | |
Claude Haiku 4.5 Anthropic | 38.9% | $0.88 | 144 |
| 4 |  |
Gemini 3.1 Pro Google | 38.7% | $1.38 | 103 |
| 5 |  |
GPT 5.4 OpenAI | 34.6% | $0.20 | 6 |
| 6 | |
Gemini 3 Flash Google | 14.8% | $0.33 | 91 |
| 7 | |
GPT 5 mini OpenAI | 10.2% | $0.01 | 9 |
| 8 | |
GPT 5.4 mini OpenAI | 7.2% | $0.39 | 323 |
| 9 | |
Claude Opus 4.7 Anthropic | 1.5% | $3.72 | 107 |
Click row to see model details