bootandy/dust
A more intuitive version of du in rust
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 Opus 4.7 Anthropic | 70.9% | $12.12 | 171 |
| 2 | |
Claude Opus 4.6 Anthropic | 70.0% | $15.78 | 245 |
| 3 | |
Claude Sonnet 4.6 Anthropic | 68.7% | $45.15 | 499 |
| 4 |  |
GPT 5.4 OpenAI | 52.2% | $0.46 | 11 |
| 5 |  |
Gemini 3.1 Pro Google | 45.7% | $1.32 | 88 |
| 6 | |
Claude Haiku 4.5 Anthropic | 42.8% | $1.46 | 164 |
| 7 | |
Gemini 3 Flash Google | 28.3% | $0.21 | 53 |
| 8 | |
GPT 5.4 mini OpenAI | 18.3% | $0.04 | 8 |
| 9 | |
GPT 5 mini OpenAI | 2.1% | $0.05 | 18 |
Click row to see model details