Benchmark Overview
87.80
0.00
89
Jun 21, 2026, 05:52 PM
Key Insights
GLM-5.2 streams at 87.80 tokens/second on average across the last 89 benchmark runs.
Performance fluctuated by 144.92 tokens/second (165.1% coefficient of variation), indicating variable behavior across benchmark runs.
Latest measurements completed on Jun 21, 2026, 05:52 PM based on 89 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.
GLM-5.2
Benchmark Samples
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| together | GLM-5.2 | 87.80 | 2.08 | 147.00 | 0.00 |
Frequently Asked Questions
The latest rolling average throughput is 87.80 tokens per second with an average time to first token of 0.00 ms across 89 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Jun 21, 2026, 05:52 PM.