YS-L/flamelens
Flamegraph viewer in the terminal
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 | 59.4% | $15.81 | 252 |
| 2 | |
Claude Sonnet 4.6 Anthropic | 57.6% | $43.26 | 490 |
| 3 | |
Claude Opus 4.7 Anthropic | 57.1% | $1.38 | 62 |
| 4 |  |
Gemini 3 Flash Google | 44.2% | $0.19 | 57 |
| 5 | |
Claude Haiku 4.5 Anthropic | 41.5% | $0.82 | 157 |
| 6 |  |
GPT 5.4 OpenAI | 21.9% | $0.07 | 7 |
| 7 | |
GPT 5.4 mini OpenAI | 17.0% | $0.01 | 8 |
| 8 | |
Gemini 3.1 Pro Google | 14.7% | $2.25 | 77 |
| 9 | |
GPT 5 mini OpenAI | 13.8% | $0.02 | 11 |
Click row to see model details