GPT-4o-mini
제공 OpenAI · 출시일 2024-07-18
39.6
평균 점수
$0.15/1M
입력 가격
$0.60/1M
출력 가격
128K tokens (~64 books)
컨텍스트 윈도우
multimodal
유형
Tested on 15 benchmarks with 39.6% average. Top scores: GSM8K (91.3%), PIQA (77.4%), MMLU (75.7%).
벤치마크 점수
| 벤치마크 | 카테고리 | 점수 | Bar |
|---|---|---|---|
| GSM8K | math | 91.3 | |
| PIQA | knowledge | 77.4 | |
| MMLU | knowledge | 75.7 | |
| Lech Mazur Writing | knowledge | 67.2 | |
| GeoBench | knowledge | 64.0 | |
| Aider — Code Editing | coding | 55.6 | |
| VideoMME | multimodal | 53.1 | |
| MATH level 5 | math | 52.6 | |
| Balrog | knowledge | 17.4 | |
| GPQA diamond | knowledge | 17.0 | |
| WeirdML | coding | 11.8 | |
| OTIS Mock AIME 2024-2025 | math | 6.8 | |
| Aider polyglot | coding | 3.6 | |
| VPCT | knowledge | 1.0 | |
| ARC-AGI-2 | reasoning | 0.1 |
유사 모델
Google DeepMind
40.0
Mistral AI
40.0
z-ai
40.1
Mistral AI
39.1