API Status

claude-3-5-haiku Benchmarks

Provider: bedrock

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 bedrock provider hub to compare every tracked model side-by-side.


Benchmark Overview

Avg Tokens / Second

31.40

Avg Time to First Token (ms)

700.00

Runs Analysed

1270

Last Updated

May 7, 2026, 11:43 PM

Key Insights

  • claude-3-5-haiku streams at 31.40 tokens/second on average across the last 1270 benchmark runs.

  • Performance fluctuated by 12.10 tokens/second (38.5% coefficient of variation), indicating variable behavior across benchmark runs.

  • Average time to first token is 700.00 ms (good latency), suitable for latency-sensitive workloads.

  • Latest measurements completed on May 7, 2026, 11:43 PM based on 1270 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)
bedrockclaude-3-5-haiku31.4023.9036.00700.00

Frequently Asked Questions

The latest rolling average throughput is 31.40 tokens per second with an average time to first token of 700.00 ms across 1270 recent runs.

Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on May 7, 2026, 11:43 PM.

Related Links