Compare LLM Models
Select 2-5 models to compare side by side.
Select models to compare
0 / 5 selected
Top downloads
Select 2-5 models
| Attribute |
z-ai
|
|---|---|
| Company | z-ai |
| Release Date | 2026-09-23 |
| Parameters (B) | 744 |
| Architecture | MoE Transformer |
| Context Window | 1000000 |
| Input Modalities | text |
| Open Source | No |
| License | |
| Score | 45 |
| VRAM (GB) | — |
| Compute | API only |
| Benchmark: AIME-2026 | 92.7 |
| Benchmark: Agents-Last-Exam | 28.5 |
| Benchmark: AutomationBench | 48.2 |
| Benchmark: BrowseComp | 75.9 |
| Benchmark: Context-Arena | 88.5 |
| Benchmark: Creative-Writing | 2075 |
| Benchmark: CyberGym | 84.5 |
| Benchmark: DeepSWE | 66.9 |
| Benchmark: GDPval-AA | 1769 |
| Benchmark: GPQA-Diamond | 88.1 |
| Benchmark: HLE | 62.5 |
| Benchmark: IFEval | 72 |
| Benchmark: IMO-AnswerBench | 82.5 |
| Benchmark: LiveBench | 76.1 |
| Benchmark: MMLU-Pro | 86.8 |
| Benchmark: NL2Repo-Bench | 58 |
| Benchmark: SWE-Bench-Pro | 95.6 |
| Benchmark: SWE-Bench-Verified | 77.8 |
| Benchmark: SimpleBench | 66.2 |
| Benchmark: Terminal-Bench-2.0 | 61.1 |
| Benchmark: Terminal-Bench-2.1 | 88.2 |
| Benchmark: Terminal-Bench-3.0 | 28.3 |
| Benchmark: Toolathlon-Verified | 73 |
| Pricing (Input) | 2.80 |
| Pricing (Output) | 8.80 |