OpenAI

GPT-4o

Multimodal
Zero-eval
#1ComplexFuncBench
#1ActivityNet
#2AI2D
+3 more

by OpenAI

About

GPT-4o is a multimodal language model developed by OpenAI. The model shows competitive results across 32 benchmarks. It excels particularly in AI2D (94.2%), DocVQA (92.8%), ChartQA (85.7%). The model shows particular specialization in vision tasks with an average performance of 82.5%. It supports a 144K token context window for handling large documents. The model is available through 3 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
Providers3
Timeline
AnnouncedAug 6, 2024
ReleasedAug 6, 2024
Specifications
Capabilities
Multimodal
License & Family
License
Proprietary
Benchmark Performance Overview
Performance metrics and category breakdown

Overall Performance

32 benchmarks
Average Score
55.1%
Best Score
94.2%
High Performers (80%+)
7

Performance Metrics

Max Context Window
144.4K
Avg Throughput
110.0 tok/s
Avg Latency
1ms

Top Categories

vision
82.5%
code
81.0%
math
61.4%
general
52.1%
agents
51.5%
Benchmark Performance
Top benchmark scores with normalized values (0-100%)
Ranking Across Benchmarks
Position relative to other models on each benchmark

AI2D

Rank #2 of 17
#1Claude 3.5 Sonnet
94.7%
#2GPT-4o
94.2%
#3Pixtral Large
93.8%
#4Mistral Small 3.2 24B Instruct
92.9%
#5Llama 3.2 90B Instruct
92.3%

DocVQA

Rank #15 of 26
#12Phi-4-multimodal-instruct
93.2%
#13Grok-2 mini
93.2%
#14Pixtral Large
93.3%
#15GPT-4o
92.8%
#16Nova Lite
92.4%
#17DeepSeek VL2 Small
92.3%
#18Pixtral-12B
90.7%

ChartQA

Rank #12 of 24
#9DeepSeek VL2
86.0%
#10Nova Lite
86.8%
#11Qwen2.5 VL 7B Instruct
87.3%
#12GPT-4o
85.7%
#13Llama 3.2 90B Instruct
85.5%
#14Qwen2.5-Omni-7B
85.3%
#15DeepSeek VL2 Small
84.5%

MMLU

Rank #27 of 78
#24Nova Pro
85.9%
#25Gemini 1.5 Pro
85.9%
#26Llama 3.3 70B Instruct
86.0%
#27GPT-4o
85.7%
#28Llama 4 Maverick
85.5%
#29o1-mini
85.2%
#30Phi 4
84.8%

CharXiv-D

Rank #4 of 5
#1GPT-4.1
87.9%
#2GPT-4.1 mini
88.4%
#3GPT-4.5
90.0%
#4GPT-4o
85.3%
#5GPT-4.1 nano
73.9%
All Benchmark Results for GPT-4o
Complete list of benchmark scores with detailed information
AI2D
AI2D benchmark
general
text
0.94
94.2%
Self-reported
DocVQA
DocVQA benchmark
vision
multimodal
0.93
92.8%
Self-reported
ChartQA
ChartQA benchmark
general
multimodal
0.86
85.7%
Self-reported
MMLU
MMLU benchmark
general
text
0.86
85.7%
Self-reported
CharXiv-D
CharXiv-D benchmark
general
text
0.85
85.3%
Self-reported
MMMLU
MMMLU benchmark
general
text
0.81
81.4%
Self-reported
IFEval
IFEval benchmark
code
text
0.81
81.0%
Self-reported
MMLU-Pro
MMLU-Pro benchmark
general
text
0.75
74.7%
Self-reported
MMMU
MMMU benchmark
vision
multimodal
0.72
72.2%
Self-reported
EgoSchema
EgoSchema benchmark
general
text
0.72
72.2%
Self-reported
Showing 1 to 10 of 32 benchmarks