llm-benchmarks
githubdrose.io

gpt-3.5-turbo-instruct-0914 Benchmarks


Measured on openai

7 runs
openai site
Avg Tokens / Second
37.50
Decode Tokens / Second
Avg Time to First Token (ms)
1430.00
Runs Analysed
7
Last Updated
Aug 12, 2026, 02:51 PM

Throughput distribution

Throughput over time

gpt-3.5-turbo-instruct-0914openai45tok/s

Generated throughput, including reasoning tokens — so a thinking model's line does not collapse; the table ranks on visible tokens · one cell per model, showing its best-covered provider · models with at least 4 samples in the window first, fastest of those at the top · shared vertical scale, 0 to 56 tok/s (99th percentile) · dashed rule is the model's own mean · 1 cell carry fewer than 4 samples

Every lane measuring this model

1 measured · live first · a lane is a provider, a catalogue id and a transport
ProviderLaneAvg Toks/SecMinMaxAvg TTF (ms)n
openaidirect · disabled37.5027.3057.901430.007

Frequently Asked Questions

How fast is gpt-3.5-turbo-instruct-0914?
The latest rolling average throughput is 37.50 tokens per second with an average time to first token of 1430.00 ms across 7 recent runs.
How often are these benchmarks updated?
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Aug 12, 2026, 02:51 PM.

Related models