GPT-4o
Multimodal
Zero-eval
by OpenAI
About
GPT-4o is a multimodal language model developed by OpenAI. It achieves strong performance with an average score of 77.4% across 8 benchmarks. It excels particularly in MGSM (90.5%), HumanEval (90.2%), MMLU (88.7%). It supports a 132K token context window for handling large documents. The model is available through 2 API providers. As a multimodal model, it can process and understand text, images, and other input formats seamlessly. Released in 2024, it represents OpenAI's latest advancement in AI technology.
Pricing Range
Input (per 1M)$2.50 -$2.50
Output (per 1M)$10.00 -$10.00
Providers2
Timeline
AnnouncedMay 13, 2024
ReleasedMay 13, 2024
Specifications
Capabilities
Multimodal
License & Family
License
Proprietary
Benchmark Performance Overview
Performance metrics and category breakdown
Overall Performance
8 benchmarks
Average Score
77.4%
Best Score
90.5%
High Performers (80%+)
4Performance Metrics
Max Context Window
132.1KAvg Throughput
96.0 tok/sAvg Latency
1msTop Categories
code
90.2%
math
77.0%
general
74.6%
Benchmark Performance
Top benchmark scores with normalized values (0-100%)
Ranking Across Benchmarks
Position relative to other models on each benchmark
MGSM
Rank #9 of 31
#6Llama 4 Scout
90.6%
#7Claude 3 Opus
90.7%
#8o1-preview
90.8%
#9GPT-4o
90.5%
#10o1
89.3%
#11GPT-4 Turbo
88.5%
#12Gemini 1.5 Pro
87.5%
HumanEval
Rank #9 of 62
#6Qwen2.5 VL 32B Instruct
91.5%
#7Mistral Large 2
92.0%
#8Claude 3.5 Sonnet
92.0%
#9GPT-4o
90.2%
#10Granite 3.3 8B Instruct
89.7%
#11Granite 3.3 8B Base
89.7%
#12Gemini Diffusion
89.6%
MMLU
Rank #10 of 78
#7Kimi K2 Instruct
89.5%
#8GPT-4.1
90.2%
#9Claude 3.5 Sonnet
90.4%
#10GPT-4o
88.7%
#11DeepSeek-V3
88.5%
#12Qwen3 235B A22B
87.8%
#13Kimi K2 Base
87.8%
DROP
Rank #8 of 28
#5Llama 3.1 405B Instruct
84.8%
#6Nova Pro
85.4%
#7GPT-4 Turbo
86.0%
#8GPT-4o
83.4%
#9Claude 3.5 Haiku
83.1%
#10Claude 3 Opus
83.1%
#11GPT-4
80.9%
MATH
Rank #19 of 63
#16Nova Pro
76.6%
#17Llama 3.3 70B Instruct
77.0%
#18Gemini 1.5 Flash
77.9%
#19GPT-4o
76.6%
#20Grok-2
76.1%
#21Gemma 3 4B
75.6%
#22Qwen2.5 7B Instruct
75.5%
All Benchmark Results for GPT-4o
Complete list of benchmark scores with detailed information
MGSM MGSM benchmark | math | text | 0.91 | 90.5% | Self-reported |
HumanEval HumanEval benchmark | code | text | 0.90 | 90.2% | Self-reported |
MMLU MMLU benchmark | general | text | 0.89 | 88.7% | Self-reported |
DROP DROP benchmark | general | text | 0.83 | 83.4% | Self-reported |
MATH MATH benchmark | math | text | 0.77 | 76.6% | Self-reported |
MMLU-Pro MMLU-Pro benchmark | general | text | 0.73 | 72.6% | Self-reported |
MathVista MathVista benchmark | math | text | 0.64 | 63.8% | Self-reported |
GPQA GPQA benchmark | general | text | 0.54 | 53.6% | Self-reported |
Resources