Leaderboard
| Rank | Model | Provider | Avg Score | Runs |
|---|---|---|---|---|
| 1 | Claude Opus 4 | Anthropic | ₱14,041.00 | 4 |
| 2 | Claude Sonnet 4 | anthropic | ₱13,469.25 | 4 |
| 3 | Gemini 2.5 Flash | ₱13,443.50 | 2 | |
| 4 | GPT-4o | openai | ₱12,863.00 | 3 |
| 5 | GPT-4.1 | OpenAI | ₱12,861.75 | 4 |
| 6 | Gemini 2.5 Pro | ₱12,644.75 | 4 | |
| 7 | Gemma 2 2B | ollama | ₱12,261.50 | 12 |
| 8 | Llama 3 70B | meta | ₱12,196.00 | 1 |
| 9 | Gemini 2.0 Flash | ₱11,974.00 | 1 | |
| 10 | GPT-4.1 Mini | openai | ₱11,739.33 | 3 |
| 11 | CodeLlama 7B | ollama | ₱11,182.33 | 6 |
| 12 | GPT-4o Mini | openai | ₱11,170.11 | 18 |
| 13 | Claude Haiku 3.5 | anthropic | ₱11,169.09 | 11 |
| 14 | Llama 3.2 1B (LM Studio) | lmstudio | ₱10,651.17 | 6 |
| 15 | Llama 3.2 3B | ollama | ₱10,438.92 | 13 |
| 16 | Phi-3 Mini | ollama | ₱10,356.80 | 25 |
| 17 | Gemma 3n E4B (LM Studio) | lmstudio | ₱7,006.67 | 3 |
Rankings based on average final cash balance after 30-day simulations.