Updated March 26, 2026· Based on independent benchmark data
Gemini 3 Pro Preview (high) and GLM-5-Turbo are virtually tied on intelligence (48.4 vs 46.8). For speed, Gemini 3 Pro Preview (high) wins at 115 tok/s vs 0 tok/s.
| Metric | Gemini 3 Pro Preview (high) | GLM-5-Turbo |
|---|---|---|
| Intelligence Score | 48.4 | 46.8 |
| Coding Score | 46.5 | 36.8 |
| Math Score | 95.7 | N/A |
| Speed (tok/s) | 115 tok/s | 0 tok/s |
| Latency (TTFT) | 36.25s | 0.00s |
| Input Price / 1M tokens | $2.00 | Free |
| Output Price / 1M tokens | $12 | Free |
| Context Window | N/A | N/A |
| Max Output Tokens | N/A | N/A |
| Input Modalities | Text | Text |
Gemini 3 Pro Preview (high) and GLM-5-Turbo perform similarly on overall intelligence, scoring 48.4 and 46.8 respectively. For coding tasks, Gemini 3 Pro Preview (high) has the edge with a coding score of 46.5 vs 36.8.
Gemini 3 Pro Preview (high) generates output significantly faster at 115 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 36.25s for Gemini 3 Pro Preview (high), which affects perceived responsiveness in interactive applications.
GLM-5-Turbo is completely free, while Gemini 3 Pro Preview (high) costs $2.00/1M input tokens and $12/1M output tokens.
Choose Gemini 3 Pro Preview (high) when you need stronger coding performance (46.5), faster output (115 tok/s).
Gemini 3 Pro Preview (high) scores higher on coding benchmarks (46.5 vs 36.8), making it the better choice for programming tasks.
Gemini 3 Pro Preview (high) is faster, producing output at 115 tok/s compared to GLM-5-Turbo's 0 tok/s.
No, Gemini 3 Pro Preview (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 |