Provider Snapshot
7
57.69
824.29
Feb 9, 2026
Key Takeaways
7 google models are actively benchmarked with 825 total measurements across 811 benchmark runs.
undefined leads the fleet with 77.40 tokens/second, while gemini-2.5-pro delivers 42.00 tok/s.
Performance varies by 84.3% across the google model lineup, indicating diverse optimization strategies for different use cases.
Avg time to first token across the fleet is 824.29 ms, showing good responsiveness for interactive applications.
The google model fleet shows consistent performance characteristics (23.5% variation coefficient), indicating standardized infrastructure.
Fastest Models
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| 77.40 | 34.90 | 113.00 | 560.00 | ||
| claude-3-haiku | 67.50 | 27.80 | 78.30 | 530.00 | |
| gemini-2.0-flash | 61.20 | 8.14 | 87.70 | 600.00 | |
| gemini-2.0-flash-lite | 60.90 | 11.70 | 80.30 | 610.00 | |
| gemini-2.5-flash | 60.00 | 7.95 | 78.00 | 1210.00 | |
| gemini-2.5-pro | 42.00 | 15.70 | 62.10 | 1540.00 |
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-2.0-flash-lite | 60.90 | 11.70 | 80.30 | 610.00 | |
| gemini-2.0-flash | 61.20 | 8.14 | 87.70 | 600.00 | |
| claude-3-5-sonnet | 34.80 | 24.40 | 45.70 | 720.00 | |
| claude-3-haiku | 67.50 | 27.80 | 78.30 | 530.00 | |
| 77.40 | 34.90 | 113.00 | 560.00 | ||
| gemini-2.5-flash | 60.00 | 7.95 | 78.00 | 1210.00 | |
| gemini-2.5-pro | 42.00 | 15.70 | 62.10 | 1540.00 |
Featured Models
Frequently Asked Questions
Based on recent tests, undefined shows the highest average throughput among tracked google models.
This provider summary aggregates 825 individual prompts measured across 811 monitoring runs over the past month.