Provider Snapshot
3
24.78
1120.00
May 20, 2026
Key Takeaways
3 google models are actively benchmarked with 497 total measurements across 463 benchmark runs.
gemini-2.5-flash-lite leads the fleet with 71.30 tokens/second, while gemini-2.5-pro delivers 1.27 tok/s.
Performance varies by 5514.2% across the google model lineup, indicating diverse optimization strategies for different use cases.
Avg time to first token across the fleet is 1120.00 ms, showing moderate responsiveness for interactive applications.
The google model fleet shows varied performance characteristics (132.7% variation coefficient), reflecting diverse model architectures.
Fastest Models
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| gemini-2.5-flash-lite | 71.30 | 26.00 | 97.00 | 540.00 | |
| gemini-2.5-flash | 1.78 | 0.48 | 3.04 | 1050.00 | |
| gemini-2.5-pro | 1.27 | 0.60 | 1.88 | 1770.00 |
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 | 1.78 | 0.48 | 3.04 | 1050.00 | |
| gemini-2.5-flash-lite | 71.30 | 26.00 | 97.00 | 540.00 | |
| gemini-2.5-pro | 1.27 | 0.60 | 1.88 | 1770.00 |
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 497 individual prompts measured across 463 monitoring runs over the past month.