Provider Snapshot
Models Tracked
2
Avg Tokens / Second
67.55
Avg Time to First Token (ms)
0.00
Last Updated
Jul 19, 2026
Key Takeaways
2 together models are actively benchmarked with 1715 total measurements across 1697 benchmark runs.
Kimi-K2.7-Code leads the fleet with 69.60 tokens/second, while GLM-5.2 delivers 65.50 tok/s.
Performance varies by 6.3% across the together model lineup, indicating diverse optimization strategies for different use cases.
Fastest Models
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| together | Kimi-K2.7-Code | 69.60 | 0.96 | 207.00 | 0.00 |
| together | GLM-5.2 | 65.50 | 1.95 | 158.00 | 0.00 |
All Models
Complete list of all together 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) |
|---|---|---|---|---|---|
| together | Kimi-K2.7-Code | 69.60 | 0.96 | 207.00 | 0.00 |
| together | GLM-5.2 | 65.50 | 1.95 | 158.00 | 0.00 |
Featured Models
Frequently Asked Questions
Based on recent tests, Kimi-K2.7-Code shows the highest average throughput among tracked together models.
This provider summary aggregates 1715 individual prompts measured across 1697 monitoring runs over the past month.