Benchmark Overview
192.00
250.00
240
Mar 19, 2026, 03:01 PM
Key Insights
llama-4-scout streams at 192.00 tokens/second on average across the last 240 benchmark runs.
Performance fluctuated by 296.50 tokens/second (154.4% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 250.00 ms (excellent latency), suitable for latency-sensitive workloads.
Latest measurements completed on Mar 19, 2026, 03:01 PM based on 240 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 | 192.00 | 38.50 | 335.00 | 250.00 |
Frequently Asked Questions
The latest rolling average throughput is 192.00 tokens per second with an average time to first token of 250.00 ms across 240 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Mar 19, 2026, 03:01 PM.