Provider Snapshot
4
30.40
1237.50
Jul 19, 2026
Key Takeaways
4 anthropic models are actively benchmarked with 2131 total measurements across 2084 benchmark runs.
claude-haiku-4.5 leads the fleet with 44.30 tokens/second, while claude-opus-4.5 delivers 21.60 tok/s.
Performance varies by 105.1% across the anthropic model lineup, indicating diverse optimization strategies for different use cases.
Avg time to first token across the fleet is 1237.50 ms, showing moderate responsiveness for interactive applications.
The anthropic model fleet shows consistent performance characteristics (29.0% variation coefficient), indicating standardized infrastructure.
Fastest Models
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| anthropic | claude-haiku-4.5 | 44.30 | 6.26 | 66.90 | 860.00 |
| anthropic | claude-opus-4-8 | 31.60 | 5.24 | 45.60 | 1320.00 |
| anthropic | claude-sonnet-4.6 | 24.10 | 7.14 | 33.60 | 1200.00 |
| anthropic | claude-opus-4.5 | 21.60 | 5.44 | 35.30 | 1570.00 |
All Models
Complete list of all anthropic 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) |
|---|---|---|---|---|---|
| anthropic | claude-haiku-4.5 | 44.30 | 6.26 | 66.90 | 860.00 |
| anthropic | claude-opus-4.5 | 21.60 | 5.44 | 35.30 | 1570.00 |
| anthropic | claude-opus-4-8 | 31.60 | 5.24 | 45.60 | 1320.00 |
| anthropic | claude-sonnet-4.6 | 24.10 | 7.14 | 33.60 | 1200.00 |
Featured Models
Frequently Asked Questions
Based on recent tests, claude-haiku-4.5 shows the highest average throughput among tracked anthropic models.
This provider summary aggregates 2131 individual prompts measured across 2084 monitoring runs over the past month.