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 |
anthropic
|
|---|---|
| Company | anthropic |
| Release Date | 2026-09-22 |
| Parameters (B) | — |
| Architecture | Transformer |
| Context Window | 1000000 |
| Input Modalities | text, image |
| Open Source | No |
| License | |
| Score | 58 |
| VRAM (GB) | — |
| Compute | API only |
| Benchmark: Agents-Last-Exam | 32.2 |
| Benchmark: AutomationBench | 50.3 |
| Benchmark: BrowseComp | 90.8 |
| Benchmark: Context-Arena | 97.7 |
| Benchmark: Creative-Writing | 2132.6 |
| Benchmark: DeepSWE | 73.7 |
| Benchmark: GDPval-AA | 1846 |
| Benchmark: GPQA-Diamond | 93.7 |
| Benchmark: HLE | 63.6 |
| Benchmark: HLE-Verified | 54.4 |
| Benchmark: LiveBench | 80.1 |
| Benchmark: MMLU | 94.3 |
| Benchmark: MMLU-Pro | 93.4 |
| Benchmark: MMMU-Pro | 84.7 |
| Benchmark: NL2Repo-Bench | 75.3 |
| Benchmark: SWE-Bench-Multilingual | 89.5 |
| Benchmark: SWE-Bench-Pro | 79.2 |
| Benchmark: SWE-Bench-Verified | 96 |
| Benchmark: SimpleBench | 80.6 |
| Benchmark: Terminal-Bench-2.1 | 89.1 |
| Benchmark: Terminal-Bench-3.0 | 43.3 |
| Benchmark: Toolathlon-Verified | 77.8 |
| Pricing (Input) | 2.00 |
| Pricing (Output) | 10.00 |