antonmedv/fx
Terminal JSON viewer & processor
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 | 75.7% | $20.74 | 396 |
| 2 | |
Claude Opus 4.7 Anthropic | 49.3% | $5.93 | 145 |
| 3 |  |
GPT 5.4 OpenAI | 49.3% | $0.20 | 10 |
| 4 |  |
Gemini 3.1 Pro Google | 42.1% | $1.37 | 127 |
| 5 | |
GPT 5.4 mini OpenAI | 40.3% | $0.03 | 7 |
| 6 | |
Claude Haiku 4.5 Anthropic | 17.5% | $0.73 | 133 |
| 7 | |
Gemini 3 Flash Google | 16.1% | $0.19 | 85 |
| 8 | |
GPT 5 mini OpenAI | 11.6% | $0.01 | 11 |
| 9 | |
Claude Sonnet 4.6 Anthropic | 4.3% | $25.98 | 621 |
Click row to see model details