# LLM Latency Benchmark Report

**Generated**: 2026-01-27 05:02:34

## Summary

| Model | TTFT (median) | Total (median) | Success Rate |
|-------|---------------|----------------|--------------|
| anthropic/claude-haiku-4-5-20251001 | 654ms | 1074ms | 100% |
| openai/gpt-5-mini | 3197ms | 3202ms | 100% |

## Detailed Results

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

**TTFT (Time to First Token)**
- Min: 654ms
- Max: 654ms
- Mean: 654ms
- Median: 654ms
- Stdev: N/A

**Total Response Time**
- Min: 1074ms
- Max: 1074ms
- Mean: 1074ms
- Median: 1074ms
- Stdev: N/A

**Individual Runs**

- Run 1: TTFT=654ms, Total=1074ms, Tokens=18

### openai/gpt-5-mini

**TTFT (Time to First Token)**
- Min: 3197ms
- Max: 3197ms
- Mean: 3197ms
- Median: 3197ms
- Stdev: N/A

**Total Response Time**
- Min: 3202ms
- Max: 3202ms
- Mean: 3202ms
- Median: 3202ms
- Stdev: N/A

**Individual Runs**

- Run 1: TTFT=3197ms, Total=3202ms, Tokens=0

## Configuration

- **Prompt**: "Write a haiku about programming."
- **Max Tokens**: 100
- **Timeout**: 60s