gpt-4o Benchmarks

Provider: openai

Explore real-world latency and throughput results for gpt-4o. 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 openai provider hub to compare every tracked model side-by-side.

Visit openai Official Website

Benchmark Overview

Avg Tokens / Second

36.10

Avg Time to First Token (ms)

430.00

Runs Analysed

239

Last Updated

Feb 20, 2026, 06:03 PM

Key Insights

  • gpt-4o streams at 36.10 tokens/second on average across the last 239 benchmark runs.

  • Performance fluctuated by 63.63 tokens/second (176.3% coefficient of variation), indicating variable behavior across benchmark runs.

  • Average time to first token is 430.00 ms (excellent latency), suitable for latency-sensitive workloads.

  • Latest measurements completed on Feb 20, 2026, 06:03 PM based on 239 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.

gpt-4o

Benchmark Samples

ProviderModelAvg Toks/SecMinMaxAvg TTF (ms)
openaigpt-4o36.107.3771.00430.00

Frequently Asked Questions

The latest rolling average throughput is 36.10 tokens per second with an average time to first token of 430.00 ms across 239 recent runs.

Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Feb 20, 2026, 06:03 PM.

Related Links