Updated March 26, 2026· Based on independent benchmark data
GPT-5.1 (high) and GLM-5-Turbo are virtually tied on intelligence (47.7 vs 46.8). For speed, GPT-5.1 (high) wins at 92 tok/s vs 0 tok/s.
| Metric | GPT-5.1 (high) | GLM-5-Turbo |
|---|---|---|
| Intelligence Score | 47.7 | 46.8 |
| Coding Score | 44.7 | 36.8 |
| Math Score | 94.0 | N/A |
| Speed (tok/s) | 92 tok/s | 0 tok/s |
| Latency (TTFT) | 39.04s | 0.00s |
| Input Price / 1M tokens | $1.25 | Free |
| Output Price / 1M tokens | $10 | Free |
| Context Window | N/A | N/A |
| Max Output Tokens | N/A | N/A |
| Input Modalities | Text | Text |
GPT-5.1 (high) and GLM-5-Turbo perform similarly on overall intelligence, scoring 47.7 and 46.8 respectively. For coding tasks, GPT-5.1 (high) has the edge with a coding score of 44.7 vs 36.8.
GPT-5.1 (high) generates output significantly faster at 92 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 39.04s for GPT-5.1 (high), which affects perceived responsiveness in interactive applications.
GLM-5-Turbo is completely free, while GPT-5.1 (high) costs $1.25/1M input tokens and $10/1M output tokens.
Choose GPT-5.1 (high) when you need stronger coding performance (44.7), faster output (92 tok/s).
GPT-5.1 (high) scores higher on coding benchmarks (44.7 vs 36.8), making it the better choice for programming tasks.
GPT-5.1 (high) is faster, producing output at 92 tok/s compared to GLM-5-Turbo's 0 tok/s.
No, GPT-5.1 (high) does not support image input. Neither model supports image input.
Both models perform similarly on intelligence benchmarks. Choose based on specific needs: pricing, speed, context window, or provider ecosystem.
Data last synced: March 26, 2026
| Output Modalities | Text | Text |
| Free Tier | No | Yes |