# LLM Latency Benchmark Report

**Generated**: 2026-01-27 05:32:16

## Summary

| Model | TTFT (median) | Total (median) | Tokens/sec | Success |
|-------|---------------|----------------|------------|---------|
| anthropic/claude-haiku-4-5-20251001 | 1817ms | 4980ms | 94.8 | 100% |

## Detailed Results

### anthropic/claude-haiku-4-5-20251001

**TTFT (Time to First Token)**
- Min: 1817ms
- Max: 1817ms
- Mean: 1817ms
- Median: 1817ms
- Stdev: N/A

**Total Response Time**
- Min: 4980ms
- Max: 4980ms
- Mean: 4980ms
- Median: 4980ms
- Stdev: N/A

**Individual Runs**

- Run 1: TTFT=1817ms, Total=4980ms, Tokens=300, 94.8 tok/s

## Configuration

- **Prompt**: "Explain how a CPU cache works in 3 paragraphs."
- **Max Tokens**: 300
- **Timeout**: 60s