# LLM Latency Benchmark Report

**Generated**: 2026-01-27 05:07:07

## Summary

| Model | TTFT (median) | Total (median) | Success Rate |
|-------|---------------|----------------|--------------|
| xai/grok-4-1-fast-non-reasoning | 485ms | 713ms | 100% |
| gemini/gemini-2.5-flash-lite | 603ms | 747ms | 100% |
| anthropic/claude-haiku-4-5-20251001 | 784ms | 1227ms | 100% |

## Detailed Results

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

**TTFT (Time to First Token)**
- Min: 442ms
- Max: 528ms
- Mean: 485ms
- Median: 485ms
- Stdev: 60ms

**Total Response Time**
- Min: 698ms
- Max: 728ms
- Mean: 713ms
- Median: 713ms
- Stdev: 22ms

**Individual Runs**

- Run 1: TTFT=442ms, Total=728ms, Tokens=20
- Run 2: TTFT=528ms, Total=698ms, Tokens=18

### gemini/gemini-2.5-flash-lite

**TTFT (Time to First Token)**
- Min: 302ms
- Max: 904ms
- Mean: 603ms
- Median: 603ms
- Stdev: 426ms

**Total Response Time**
- Min: 420ms
- Max: 1074ms
- Mean: 747ms
- Median: 747ms
- Stdev: 462ms

**Individual Runs**

- Run 1: TTFT=904ms, Total=1074ms, Tokens=3
- Run 2: TTFT=302ms, Total=420ms, Tokens=3

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

**TTFT (Time to First Token)**
- Min: 629ms
- Max: 938ms
- Mean: 784ms
- Median: 784ms
- Stdev: 219ms

**Total Response Time**
- Min: 1048ms
- Max: 1406ms
- Mean: 1227ms
- Median: 1227ms
- Stdev: 254ms

**Individual Runs**

- Run 1: TTFT=938ms, Total=1406ms, Tokens=16
- Run 2: TTFT=629ms, Total=1048ms, Tokens=16

## Configuration

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