Benchmark Overview
190.00
270.00
123
Feb 2, 2026, 06:01 PM
Key Insights
llama-4-scout streams at 190.00 tokens/second on average across the last 123 benchmark runs.
Performance fluctuated by 231.90 tokens/second (122.1% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 270.00 ms (excellent latency), suitable for latency-sensitive workloads.
Latest measurements completed on Feb 2, 2026, 06:01 PM based on 123 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.
llama-4-scout
Benchmark Samples
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| groq | llama-4-scout | 190.00 | 23.10 | 255.00 | 270.00 |
Frequently Asked Questions
The latest rolling average throughput is 190.00 tokens per second with an average time to first token of 270.00 ms across 123 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Feb 2, 2026, 06:01 PM.