sitkevij/hex
🔮 Futuristic take on hexdump, made 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 | Gemini 3.1 Pro Google | 91.7% | $1.25 | 84 | |
| 2 | Claude Sonnet 4.6 Anthropic | 72.3% | $11.60 | 392 | |
| 3 | Claude Opus 4.6 Anthropic | 71.3% | $5.97 | 227 | |
| 4 | GPT 5.4 OpenAI | 67.2% | $0.19 | 9 | |
| 5 | Claude Opus 4.7 Anthropic | 66.3% | $2.75 | 89 | |
| 6 | Gemini 3 Flash Google | 66.1% | $0.34 | 124 | |
| 7 | GPT 5.4 mini OpenAI | 36.1% | $0.03 | 13 | |
| 8 | Claude Haiku 4.5 Anthropic | 28.7% | $0.63 | 114 | |
| 9 | GPT 5 mini OpenAI | 4.4% | $0.03 | 21 |
Click row to see model details