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 |
qwen
|
|---|---|
| Company | qwen |
| Release Date | 2026-09-23 |
| Parameters (B) | 2400 |
| Architecture | Mixture-of-Experts Transformer |
| Context Window | 1000000 |
| Input Modalities | text, image, video |
| Open Source | No |
| License | |
| Score | 0 |
| VRAM (GB) | — |
| Compute | API only |
| Benchmark: AIME-2025 | 81.5 |
| Benchmark: Agents-Last-Exam | 27 |
| Benchmark: Arena-Elo | 1502 |
| Benchmark: AutomationBench | 27.3 |
| Benchmark: Context-Arena | 96.9 |
| Benchmark: DeepSWE | 56.6 |
| Benchmark: GPQA-Diamond | 92.6 |
| Benchmark: HLE | 56.2 |
| Benchmark: IFEval | 82.8 |
| Benchmark: LiveBench | 78.5 |
| Benchmark: LiveCodeBench | 90.3 |
| Benchmark: MMLU-Pro | 88.6 |
| Benchmark: MMMU-Pro | 82.3 |
| Benchmark: NL2Repo-Bench | 55.9 |
| Benchmark: SWE-Bench-Pro | 67.7 |
| Benchmark: SWE-Bench-Verified | 87.3 |
| Benchmark: SimpleBench | 62.5 |
| Benchmark: Terminal-Bench-2.1 | 86.6 |
| Benchmark: Toolathlon-Verified | 72.5 |
| Pricing (Input) | 4.00 |
| Pricing (Output) | 12.00 |