Claude Sonnet 4.5 vs gpt-oss-120b
Côte à côte. Chaque métrique. Chaque benchmark.
| Type | Claude Sonnet 4.5 | gpt-oss-120b |
|---|---|---|
| Provider |  Anthropic |  OpenAI |
| score moyen | 42.1 | 46.9 |
| Prix d'entrée | $3.00 | $0.04 |
| Prix de sortie | $15.00 | $0.19 |
| Fenêtre de contexte | 1.0M tokens (~500 books) | 131K tokens (~66 books) |
| Sorti le | 2025-09-29 | 2025-08-05 |
| Code source ouvert | Proprietary | Open Source |
Scores de benchmark
8 benchmarks · Claude Sonnet 4.5: 5, gpt-oss-120b: 3
| Benchmark | Catégorie | Claude Sonnet 4.5 | gpt-oss-120b |
|---|---|---|---|
| Chess Puzzles | knowledge | 12.0 | 20.0 |
| GPQA diamond | knowledge | 76.4 | 67.7 |
| OTIS Mock AIME 2024-2025 | math | 77.8 | 88.9 |
| SimpleBench | reasoning | 45.2 | 6.5 |
| SimpleQA Verified | knowledge | 23.6 | 13.9 |
| SWE-Bench Verified (Bash Only) | coding | 70.6 | 26.0 |
| Terminal Bench | coding | 46.5 | 18.7 |
| WeirdML | coding | 47.7 | 48.2 |