# LLM Latency Benchmark Report

**Generated**: 2026-01-27 05:05:40

## Summary

| Model | TTFT (median) | Total (median) | Success Rate |
|-------|---------------|----------------|--------------|
| xai/grok-4-1-fast-non-reasoning | 414ms | 627ms | 100% |
| anthropic/claude-haiku-4-5-20251001 | 600ms | 960ms | 100% |
| gemini/gemini-3-flash-preview | 1034ms | 1084ms | 100% |
| openai/gpt-5-mini | 2407ms | 2422ms | 100% |

## Detailed Results

### xai/grok-4-1-fast-non-reasoning

**TTFT (Time to First Token)**
- Min: 342ms
- Max: 485ms
- Mean: 414ms
- Median: 414ms
- Stdev: 101ms

**Total Response Time**
- Min: 572ms
- Max: 682ms
- Mean: 627ms
- Median: 627ms
- Stdev: 78ms

**Individual Runs**

- Run 1: TTFT=485ms, Total=682ms, Tokens=20
- Run 2: TTFT=342ms, Total=572ms, Tokens=20

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

**TTFT (Time to First Token)**
- Min: 416ms
- Max: 784ms
- Mean: 600ms
- Median: 600ms
- Stdev: 260ms

**Total Response Time**
- Min: 868ms
- Max: 1053ms
- Mean: 960ms
- Median: 960ms
- Stdev: 131ms

**Individual Runs**

- Run 1: TTFT=784ms, Total=1053ms, Tokens=11
- Run 2: TTFT=416ms, Total=868ms, Tokens=18

### gemini/gemini-3-flash-preview

**TTFT (Time to First Token)**
- Min: 794ms
- Max: 1275ms
- Mean: 1034ms
- Median: 1034ms
- Stdev: 341ms

**Total Response Time**
- Min: 796ms
- Max: 1372ms
- Mean: 1084ms
- Median: 1084ms
- Stdev: 407ms

**Individual Runs**

- Run 1: TTFT=1275ms, Total=1372ms, Tokens=2
- Run 2: TTFT=794ms, Total=796ms, Tokens=2

### openai/gpt-5-mini

**TTFT (Time to First Token)**
- Min: 1673ms
- Max: 3142ms
- Mean: 2407ms
- Median: 2407ms
- Stdev: 1038ms

**Total Response Time**
- Min: 1689ms
- Max: 3155ms
- Mean: 2422ms
- Median: 2422ms
- Stdev: 1036ms

**Individual Runs**

- Run 1: TTFT=3142ms, Total=3155ms, Tokens=0
- Run 2: TTFT=1673ms, Total=1689ms, Tokens=0

## Configuration

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