wfxr/code-minimap
🛰 A high performance code minimap render.
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 | 88.8% | $9.23 | 184 |
| 2 | |
Claude Opus 4.6 Anthropic | 85.6% | $9.41 | 236 |
| 3 |  |
Gemini 3.1 Pro Google | 73.5% | $1.82 | 186 |
| 4 | |
Claude Sonnet 4.6 Anthropic | 71.6% | $14.48 | 348 |
| 5 | |
Gemini 3 Flash Google | 53.0% | $0.26 | 107 |
| 6 | |
Claude Haiku 4.5 Anthropic | 49.2% | $0.98 | 131 |
| 7 |  |
GPT 5.4 OpenAI | 38.0% | $0.25 | 11 |
| 8 | |
GPT 5 mini OpenAI | 19.2% | $0.09 | 43 |
| 9 | |
GPT 5.4 mini OpenAI | 0.0% | $0.06 | 11 |
Click row to see model details