Math Reasoning Recommendation: GPT-4o (2024-08-06)
Math Reasoning → GPT-4o (2024-08-06)
Use Case Overview
GPT-4o (2024-08-06) by Openai is a recommended option for the Math Reasoning use case.
Recommended Models
| Rank | Vendor | Context Window | Score |
|---|
| #5 | Openai | 128K | 57/100 |
| Benchmark | Score |
|---|
| MMLU | 87.6 |
| HUMANEVAL | 85.1 |
| GSM8K | 93.3 |
| MATH | 68.2 |
| BBH | 84.9 |
| GPQA | 62.0 |
Strengths
- MMLU score 87.6, strong knowledge reasoning.
- HumanEval 85.1, excellent code generation.
- GSM8K 93.3, robust math reasoning.
- Input Modalities: text, image, audio.
Requirements
- API key from openai
- Input length within 128K context window