Provider Snapshot
3
59.83
1066.67
May 10, 2026
Key Takeaways
3 google models are actively benchmarked with 660 total measurements across 607 benchmark runs.
gemini-2.5-flash-lite leads the fleet with 79.10 tokens/second, while gemini-2.5-pro delivers 39.40 tok/s.
Performance varies by 100.8% across the google model lineup, indicating diverse optimization strategies for different use cases.
Avg time to first token across the fleet is 1066.67 ms, showing moderate responsiveness for interactive applications.
The google model fleet shows consistent performance characteristics (27.1% variation coefficient), indicating standardized infrastructure.
Fastest Models
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| gemini-2.5-flash-lite | 79.10 | 37.70 | 114.00 | 500.00 | |
| gemini-2.5-flash | 61.00 | 0.64 | 98.60 | 1000.00 | |
| gemini-2.5-pro | 39.40 | 0.60 | 58.90 | 1700.00 |
All Models
Complete list of all google models tracked in the benchmark system. Click any model name to view detailed performance data.
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| gemini-2.5-flash | 61.00 | 0.64 | 98.60 | 1000.00 | |
| gemini-2.5-flash-lite | 79.10 | 37.70 | 114.00 | 500.00 | |
| gemini-2.5-pro | 39.40 | 0.60 | 58.90 | 1700.00 |
Featured Models
Frequently Asked Questions
Based on recent tests, gemini-2.5-flash-lite shows the highest average throughput among tracked google models.
This provider summary aggregates 660 individual prompts measured across 607 monitoring runs over the past month.