# Math Operations Test Results

## Highscores

### Performance Rankings (Duration)

| Test | Model | Duration (ms) | Duration (s) |
|------|-------|--------------|--------------|
| quadratic | openai/gpt-4o-mini | 1088 | 1.09 |
| quadratic | openai/gpt-3.5-turbo | 1202 | 1.20 |
| factorial | openai/gpt-4o-mini | 481 | 0.48 |
| factorial | openai/gpt-3.5-turbo | 503 | 0.50 |
| fibonacci | openai/gpt-3.5-turbo | 503 | 0.50 |
| fibonacci | openai/gpt-4o-mini | 601 | 0.60 |
| square_root | openai/gpt-4o-mini | 539 | 0.54 |
| square_root | openai/gpt-3.5-turbo | 738 | 0.74 |
| power | openai/gpt-3.5-turbo | 592 | 0.59 |
| power | openai/gpt-4o-mini | 1103 | 1.10 |

## Summary

- Total Tests: 10
- Passed: 9
- Failed: 1
- Success Rate: 90.00%
- Average Duration: 735ms (0.73s)

## Failed Tests

### quadratic - openai/gpt-3.5-turbo

- Prompt: `Solve the quadratic equation x² + 5x + 6 = 0. Respond ONLY with the solutions as comma-separated numbers (e.g., -3,-2). No other text.`
- Expected: `-3,-2`
- Actual: `-2,-3`
- Duration: 1202ms (1.20s)
- Reason: Expected -3,-2, but got -2,-3
- Timestamp: 6/5/2025, 8:46:07 PM

## Passed Tests

### quadratic - openai/gpt-4o-mini

- Prompt: `Solve the quadratic equation x² + 5x + 6 = 0. Respond ONLY with the solutions as comma-separated numbers (e.g., -3,-2). No other text.`
- Expected: `-3,-2`
- Actual: `-3,-2`
- Duration: 1088ms (1.09s)
- Timestamp: 6/5/2025, 8:46:09 PM

### factorial - openai/gpt-3.5-turbo

- Prompt: `Calculate 5! (factorial of 5). Respond ONLY with the final numerical answer. No explanation, no other text.`
- Expected: `120`
- Actual: `120`
- Duration: 503ms (0.50s)
- Timestamp: 6/5/2025, 8:46:09 PM

### factorial - openai/gpt-4o-mini

- Prompt: `Calculate 5! (factorial of 5). Respond ONLY with the final numerical answer. No explanation, no other text.`
- Expected: `120`
- Actual: `120`
- Duration: 481ms (0.48s)
- Timestamp: 6/5/2025, 8:46:10 PM

### fibonacci - openai/gpt-3.5-turbo

- Prompt: `Calculate the 6th number in the Fibonacci sequence (assuming F(1)=1, F(2)=1). Respond ONLY with the final numerical answer. No other text.`
- Expected: `8`
- Actual: `8`
- Duration: 503ms (0.50s)
- Timestamp: 6/5/2025, 8:46:10 PM

### fibonacci - openai/gpt-4o-mini

- Prompt: `Calculate the 6th number in the Fibonacci sequence (assuming F(1)=1, F(2)=1). Respond ONLY with the final numerical answer. No other text.`
- Expected: `8`
- Actual: `8`
- Duration: 601ms (0.60s)
- Timestamp: 6/5/2025, 8:46:11 PM

### square_root - openai/gpt-3.5-turbo

- Prompt: `Calculate the square root of 16. Respond ONLY with the final numerical answer. No other text.`
- Expected: `4`
- Actual: `4`
- Duration: 738ms (0.74s)
- Timestamp: 6/5/2025, 8:46:11 PM

### square_root - openai/gpt-4o-mini

- Prompt: `Calculate the square root of 16. Respond ONLY with the final numerical answer. No other text.`
- Expected: `4`
- Actual: `4`
- Duration: 539ms (0.54s)
- Timestamp: 6/5/2025, 8:46:12 PM

### power - openai/gpt-3.5-turbo

- Prompt: `Calculate 2 raised to the power of 3. Respond ONLY with the final numerical answer. No other text.`
- Expected: `8`
- Actual: `8`
- Duration: 592ms (0.59s)
- Timestamp: 6/5/2025, 8:46:12 PM

### power - openai/gpt-4o-mini

- Prompt: `Calculate 2 raised to the power of 3. Respond ONLY with the final numerical answer. No other text.`
- Expected: `8`
- Actual: `8`
- Duration: 1103ms (1.10s)
- Timestamp: 6/5/2025, 8:46:14 PM