Provider Snapshot
6
41.53
1.06
Oct 18, 2025
Key Takeaways
6 google models are actively benchmarked with 3887 total measurements across 3847 benchmark runs.
gemini-2.0-flash-lite leads the fleet with 65.20 tokens/second, while claude-3-opus delivers 11.30 tok/s.
Performance varies by 477.0% across the google model lineup, indicating diverse optimization strategies for different use cases.
Median time to first token across the fleet is 1.06 ms, showing excellent responsiveness for interactive applications.
The google model fleet shows varied performance characteristics (51.4% variation coefficient), reflecting diverse model architectures.
Fastest Models
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| gemini-2.0-flash-lite | 65.20 | 20.90 | 88.90 | 0.45 | |
| gemini-2.0-flash | 64.00 | 4.78 | 94.90 | 0.56 | |
| claude-3-haiku | 55.90 | 16.40 | 77.40 | 0.76 | |
| claude-3-5-sonnet | 33.10 | 12.60 | 44.10 | 0.96 | |
| claude-3-5-haiku | 19.70 | 19.70 | 19.70 | 1.41 | |
| claude-3-opus | 11.30 | 7.78 | 13.90 | 2.21 |
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) |
|---|---|---|---|---|---|
| claude-3-haiku | 55.90 | 16.40 | 77.40 | 0.76 | |
| claude-3-5-sonnet | 33.10 | 12.60 | 44.10 | 0.96 | |
| claude-3-opus | 11.30 | 7.78 | 13.90 | 2.21 | |
| gemini-2.0-flash | 64.00 | 4.78 | 94.90 | 0.56 | |
| gemini-2.0-flash-lite | 65.20 | 20.90 | 88.90 | 0.45 | |
| claude-3-5-haiku | 19.70 | 19.70 | 19.70 | 1.41 |
Featured Models
Frequently Asked Questions
Based on recent tests, gemini-2.0-flash-lite shows the highest average throughput among tracked google models.
This provider summary aggregates 3887 individual prompts measured across 3847 monitoring runs over the past month.