Updated March 26, 2026· Based on independent benchmark data
GLM-5-Turbo leads in intelligence with a score of 46.8 vs 44.6. For speed, GPT-5 Codex (high) wins at 180 tok/s vs 0 tok/s.
| Metric | GLM-5-Turbo | GPT-5 Codex (high) |
|---|---|---|
| Intelligence Score | 46.8 | 44.6 |
| Coding Score | 36.8 | 38.9 |
| Math Score | N/A | 98.7 |
| Speed (tok/s) | 0 tok/s | 180 tok/s |
| Latency (TTFT) | 0.00s | 9.17s |
| Input Price / 1M tokens | Free | $1.25 |
| Output Price / 1M tokens | Free | $10 |
| Context Window | N/A | N/A |
| Max Output Tokens | N/A | N/A |
| Input Modalities | Text | Text |
GLM-5-Turbo outperforms GPT-5 Codex (high) on the intelligence index with a score of 46.8 compared to 44.6. For coding tasks, GPT-5 Codex (high) has the edge with a coding score of 38.9 vs 36.8.
GPT-5 Codex (high) generates output significantly faster at 180 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 9.17s for GPT-5 Codex (high), which affects perceived responsiveness in interactive applications.
GLM-5-Turbo is completely free, while GPT-5 Codex (high) costs $1.25/1M input tokens and $10/1M output tokens.
Choose GLM-5-Turbo when you need higher intelligence (46.8). Choose GPT-5 Codex (high) when you need stronger coding performance (38.9), faster output (180 tok/s).
GPT-5 Codex (high) scores higher on coding benchmarks (38.9 vs 36.8), making it the better choice for programming tasks.
GPT-5 Codex (high) is faster, producing output at 180 tok/s compared to GLM-5-Turbo's 0 tok/s.
No, GLM-5-Turbo does not support image input. Neither model supports image input.
It depends on your priorities. GLM-5-Turbo scores higher on intelligence (46.8), but GPT-5 Codex (high) 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 | Yes | No |