Side by side
| Qwen3.8 Max (0902) | GLM 5.2 | |
|---|---|---|
| Lab | Qwen | Z.AI |
| Listed | Sep 3, 2026 | Jun 16, 2026 |
| Input per 1M tokens | $3.00 | $0.015 |
| Output per 1M tokens | $9.00 | $10.20 |
| Cached input per 1M | $0.38 | $0.013 |
| Blended (3:1) per 1M | $4.50 | $2.56 |
| Context window | 1M | 1M |
| Max output | 131K | 944K |
| Knowledge cutoff | - | - |
| Intelligence index | 33.7 | 34 |
| Coding index | 76.2 | 68.8 |
| Reasoning | Yes | Yes |
| Reads images | Yes | No |
| Tool use | Yes | Yes |
| Structured output | Yes | Yes |
Every benchmark both are scored on
Each model's best score per benchmark, with its source. Scores from different sources or settings are not always comparable; each links to where it was published.
| Benchmark | Qwen3.8 Max (0902) | GLM 5.2 | Leader |
|---|---|---|---|
| AIME | 100%Epoch AI | 28.9%Epoch AI | Qwen3.8 Max (0902) |
| Artificial Analysis Agentic Index | 56Artificial Analysis and OpenRouter | 38.4Artificial Analysis and OpenRouter | Qwen3.8 Max (0902) |
| Artificial Analysis Coding Index | 76.2Artificial Analysis and OpenRouter | 68.8Artificial Analysis and OpenRouter | Qwen3.8 Max (0902) |
| Artificial Analysis Intelligence Index | 33.7Artificial Analysis and OpenRouter | 34Artificial Analysis and OpenRouter | GLM 5.2 |
| Chess Puzzles | 37%Epoch AI | 22%Epoch AI | Qwen3.8 Max (0902) |
| FrontierMath Tier 4 (v2) | 34.1%Epoch AI | 29.3%Epoch AI | Qwen3.8 Max (0902) |
| FrontierMath Tiers 1-3 (v2) | 65.6%Epoch AI | 42.5%Epoch AI | Qwen3.8 Max (0902) |
| GPQA Diamond | 92.3%Epoch AI | 84.9%Artificial Analysis and OpenRouter | Qwen3.8 Max (0902) |
| LMArena (Coding) | 1501 EloLMArena | 1488 EloLMArena | Qwen3.8 Max (0902) |
| LMArena (Overall) | 1481 EloLMArena | 1469 EloLMArena | Qwen3.8 Max (0902) |
| SciCode | 52.1%Epoch AI | 51.2%Epoch AI | Qwen3.8 Max (0902) |
| SimpleQA Verified | 47.3%Epoch AI | 34.2%Epoch AI | Qwen3.8 Max (0902) |
More comparisons
Where these figures come from
Prices are GenMagic's own, what the studio and the API charge, recomputed from each provider's price list every few minutes. The indices are the Artificial Analysis indices, and every benchmark score links to its source, re-read daily. Measured speed is GenMagic's own generation records, in aggregate. See Qwen models, Z.AI models, every LLM's price and our sources.