Updated March 26, 2026· Based on independent benchmark data
GPT-5.2 (xhigh) leads in intelligence with a score of 51.3 vs 46.8. For speed, GPT-5.2 (xhigh) wins at 70 tok/s vs 0 tok/s.
| Metric | GPT-5.2 (xhigh) | GLM-5-Turbo |
|---|---|---|
| Intelligence Score | 51.3 | 46.8 |
| Coding Score | 48.7 | 36.8 |
| Math Score | 99.0 | N/A |
| Speed (tok/s) | 70 tok/s | 0 tok/s |
| Latency (TTFT) | 75.24s | 0.00s |
| Input Price / 1M tokens | $1.75 | Free |
| Output Price / 1M tokens | $14 | Free |
| Context Window | N/A | N/A |
| Max Output Tokens | N/A | N/A |
| Input Modalities | Text | Text |
GPT-5.2 (xhigh) outperforms GLM-5-Turbo on the intelligence index with a score of 51.3 compared to 46.8. For coding tasks, GPT-5.2 (xhigh) has the edge with a coding score of 48.7 vs 36.8.
GPT-5.2 (xhigh) generates output significantly faster at 70 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 75.24s for GPT-5.2 (xhigh), which affects perceived responsiveness in interactive applications.
GLM-5-Turbo is completely free, while GPT-5.2 (xhigh) costs $1.75/1M input tokens and $14/1M output tokens.
Choose GPT-5.2 (xhigh) when you need higher intelligence (51.3), stronger coding performance (48.7), faster output (70 tok/s).
GPT-5.2 (xhigh) scores higher on coding benchmarks (48.7 vs 36.8), making it the better choice for programming tasks.
GPT-5.2 (xhigh) is faster, producing output at 70 tok/s compared to GLM-5-Turbo's 0 tok/s.
No, GPT-5.2 (xhigh) does not support image input. Neither model supports image input.
It depends on your priorities. GPT-5.2 (xhigh) scores higher on intelligence (51.3), 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 |