brocode/fblog
Small command-line JSON Log viewer
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 4.6 Anthropic | 86.0% | $12.29 | 304 |
| 2 | |
Claude Opus 4.7 Anthropic | 74.4% | $5.12 | 127 |
| 3 |  |
Gemini 3.1 Pro Google | 66.7% | $1.92 | 122 |
| 4 | |
Claude Haiku 4.5 Anthropic | 38.9% | $0.96 | 144 |
| 5 |  |
GPT 5 mini OpenAI | 28.9% | $0.02 | 20 |
| 6 | |
GPT 5.4 mini OpenAI | 10.1% | $0.05 | 20 |
| 7 | |
Claude Sonnet 4.6 Anthropic | 1.3% | $13.91 | 400 |
| 8 | |
GPT 5.4 OpenAI | 1.2% | $0.24 | 8 |
| 9 | |
Gemini 3 Flash Google | 1.2% | $0.24 | 77 |
Click row to see model details