Claude Opus 4.6 vs o3
Lado a lado. Cada métrica. Cada benchmark.
| Tipo | Claude Opus 4.6 | o3 |
|---|---|---|
| Provider |  Anthropic |  OpenAI |
| pontuação média | 57.5 | 55.2 |
| Preço de entrada | $5.00 | $2.00 |
| Preço de saída | $25.00 | $8.00 |
| Janela de contexto | 1.0M tokens (~500 books) | 200K tokens (~100 books) |
| Lançado em | 2026-02-04 | 2025-04-16 |
| Código aberto | Proprietary | Proprietary |
Pontuações de benchmark
12 benchmarks · Claude Opus 4.6: 11, o3: 1
| Benchmark | Categoria | Claude Opus 4.6 | o3 |
|---|---|---|---|
| ARC-AGI | reasoning | 94.0 | 60.8 |
| ARC-AGI-2 | reasoning | 69.2 | 6.5 |
| FrontierMath-2025-02-28-Private | math | 40.7 | 18.7 |
| FrontierMath-Tier-4-2025-07-01-Private | math | 22.9 | 2.1 |
| GPQA diamond | knowledge | 87.4 | 75.8 |
| GSO-Bench | coding | 33.3 | 8.8 |
| HLE | knowledge | 31.1 | 16.3 |
| OTIS Mock AIME 2024-2025 | math | 94.4 | 83.9 |
| SimpleBench | reasoning | 61.1 | 43.7 |
| SimpleQA Verified | knowledge | 46.5 | 53.0 |
| SWE-Bench verified | coding | 78.7 | 62.3 |
| WeirdML | coding | 77.9 | 52.4 |