Measured over the last 30 days
- Models Tracked
- 23
- Avg Tokens / Second
- 13.20
- Avg Time to First Token (ms)
- 12324.57
- Last Updated
- Sep 2, 2026
All gmicloud models
23 tracked · fastest first| Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|
| GLM 5 | 25.60 | 25.60 | 25.60 | 1900.00 |
| GLM 5.2 | 20.80 | 17.50 | 25.60 | 2260.00 |
| GLM 5.1 | 20.40 | 19.60 | 21.30 | 2260.00 |
| GLM 5.1 | 18.90 | 0.43 | 32.10 | 6790.00 |
| MiniMax M3 | 18.80 | 15.30 | 23.30 | 3200.00 |
| GLM 5.2 | 17.30 | 2.32 | 30.80 | 3700.00 |
| Qwen3 235B A22B Instruct 2507 | 16.40 | 16.40 | 16.40 | 2090.00 |
| DeepSeek V3.2 | 16.30 | 4.01 | 23.40 | 3320.00 |
| DeepSeek V3.2 | 15.80 | 4.55 | 21.10 | 4020.00 |
| MiMo-V2.5-Pro | 14.90 | 14.90 | 14.90 | 3090.00 |
| DeepSeek V3 0324 | 14.10 | 14.10 | 14.10 | 2730.00 |
| GLM 5 | 12.50 | 5.14 | 20.90 | 5700.00 |
| DeepSeek V4 Flash 0731 | 12.10 | 4.56 | 19.70 | 6120.00 |
| DeepSeek V4 Flash 0423 | 10.00 | 6.54 | 14.20 | 6490.00 |
| DeepSeek V4 Flash 0731 | 9.00 | 3.91 | 15.20 | 8670.00 |
| MiMo-V2.5 | 8.82 | 5.31 | 11.10 | 6890.00 |
| MiMo-V2.5-Pro | 7.89 | 7.89 | 7.89 | 5850.00 |
| MiniMax M2.7 | 5.72 | 2.84 | 9.15 | 13100.00 |
| MiniMax M2.7 | 5.23 | 2.07 | 9.03 | 14600.00 |
| Hy3 | 3.66 | 3.24 | 4.29 | 17300.00 |
| DeepSeek V4 Pro 0813 | 2.76 | 2.76 | 2.76 | 22000.00 |
| Kimi K2.6 | 1.65 | 1.65 | 1.65 | 36300.00 |
| Kimi K2.7 Code | 1.29 | 1.29 | 1.29 | 47700.00 |
Frequently Asked Questions
Which gmicloud model is fastest?
Based on recent tests, GLM 5 shows the highest average throughput among tracked gmicloud models.
How many recent measurements feed this dashboard?
This provider summary aggregates 3963 individual prompts measured across 3530 monitoring runs over the past month.