claude-3-5-haiku Benchmarks

Provider: google

Explore real-world latency and throughput results for claude-3-5-haiku. These measurements come from automated benchmarking runs against the provider APIs using the same harness that powers the public cloud dashboard.

Want a broader view of this vendor? Visit the google provider hub to compare every tracked model side-by-side.

Visit google Official Website

Benchmark Overview

Avg Tokens / Second

19.70

Avg Time to First Token (ms)

1.41

Runs Analysed

1

Last Updated

Oct 15, 2025, 04:38 AM

Key Insights

  • claude-3-5-haiku streams at 19.70 tokens/second on average across the last 1 benchmark runs.

  • Performance fluctuated by 0.00 tokens/second (0.0% coefficient of variation), indicating consistent behavior across benchmark runs.

  • Average time to first token is 1.41 ms (excellent latency), suitable for latency-sensitive workloads.

  • Latest measurements completed on Oct 15, 2025, 04:38 AM based on 1 total samples.

Performance Distribution

Distribution of throughput measurements showing performance consistency across benchmark runs.

Performance Over Time

Historical performance trends showing how throughput has changed over the benchmarking period.

claude-3-5-haiku

Benchmark Samples

ProviderModelAvg Toks/SecMinMaxAvg TTF (ms)
googleclaude-3-5-haiku19.7019.7019.701.41

Frequently Asked Questions

The latest rolling average throughput is 19.70 tokens per second with an average time to first token of 1.41 ms across 1 recent runs.

Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Oct 15, 2025, 04:38 AM.

Related Links