Updated March 26, 2026· Based on independent benchmark data
GLM-5 (Reasoning) leads in intelligence with a score of 49.8 vs 46.8. For speed, GLM-5 (Reasoning) wins at 66 tok/s vs 0 tok/s.
| Metric | GLM-5 (Reasoning) | GLM-5-Turbo |
|---|---|---|
| Intelligence Score | 49.8 | 46.8 |
| Coding Score | 44.2 | 36.8 |
| Math Score | N/A | N/A |
| Speed (tok/s) | 66 tok/s | 0 tok/s |
| Latency (TTFT) | 0.98s | 0.00s |
| Input Price / 1M tokens | $1.00 | Free |
| Output Price / 1M tokens | $3.20 | Free |
| Context Window | N/A | N/A |
| Max Output Tokens | N/A | N/A |
| Input Modalities | Text | Text |
GLM-5 (Reasoning) outperforms GLM-5-Turbo on the intelligence index with a score of 49.8 compared to 46.8. For coding tasks, GLM-5 (Reasoning) has the edge with a coding score of 44.2 vs 36.8.
GLM-5 (Reasoning) generates output significantly faster at 66 tok/s compared to GLM-5-Turbo's 0 tok/s, making it Infinityx faster for streaming responses. Time to first token is 0.00s for GLM-5-Turbo vs 0.98s for GLM-5 (Reasoning), which affects perceived responsiveness in interactive applications.
GLM-5-Turbo is completely free, while GLM-5 (Reasoning) costs $1.00/1M input tokens and $3.20/1M output tokens.
Choose GLM-5 (Reasoning) when you need higher intelligence (49.8), stronger coding performance (44.2), faster output (66 tok/s).
GLM-5 (Reasoning) scores higher on coding benchmarks (44.2 vs 36.8), making it the better choice for programming tasks.
GLM-5 (Reasoning) is faster, producing output at 66 tok/s compared to GLM-5-Turbo's 0 tok/s.
No, GLM-5 (Reasoning) does not support image input. Neither model supports image input.
It depends on your priorities. GLM-5 (Reasoning) scores higher on intelligence (49.8), but GLM-5-Turbo may be better for specific use cases like cost savings or speed-critical applications.
Data last synced: March 26, 2026
| Output Modalities | Text | Text |
| Free Tier | No | Yes |