GPT-4o (2024-05-13)
von OpenAI · Veroeffentlicht 2024-05-13
51.1
Durchschn. Score
$5.00/1M
Eingabepreis
$15.00/1M
Ausgabepreis
128K tokens (~64 books)
Kontextfenster
multimodal
Typ
Tested on 8 benchmarks with 51.1% average. Top scores: Chatbot Arena Elo — Overall (1345.1%), ScienceQA (84.7%), MMLU (78.9%).
Benchmark-Ergebnisse
| Benchmark | Kategorie | Score | Bar |
|---|---|---|---|
| Chatbot Arena Elo — Overall | arena | 1345.1 | |
| ScienceQA | knowledge | 84.7 | |
| MMLU | knowledge | 78.9 | |
| Aider — Code Editing | coding | 72.9 | |
| MATH level 5 | math | 51.0 | |
| Balrog | knowledge | 32.3 | |
| GPQA diamond | knowledge | 31.9 | |
| OTIS Mock AIME 2024-2025 | math | 6.2 |
Aehnliche Modelle
DeepSeek
51.1
OpenAI
51.0
Google DeepMind
50.9
z-ai
50.8