OpenAI

GPT-4o

Multimodal
Zero-eval
#1ComplexFuncBench
#1ActivityNet
#2AI2D
+5 more

by OpenAI

+
+
+
+
About

This updated version of GPT-4o was released with refinements to its multimodal capabilities and improved performance across text, vision, and audio tasks. Built to incorporate learnings from the initial GPT-4o deployment, it enhanced reliability and accuracy while maintaining the seamless cross-modal reasoning that defines the GPT-4o family.

+
+
+
+
Pricing Range
Input (per 1M)$2.50 -$2.50
Output (per 1M)$10.00 -$10.00
Providers2
+
+
+
+
Timeline
AnnouncedAug 6, 2024
ReleasedAug 6, 2024
+
+
+
+
Specifications
Capabilities
Multimodal
+
+
+
+
License & Family
License
Proprietary
Performance Overview
Performance metrics and category breakdown

Overall Performance

39 benchmarks
Average Score
52.8%
Best Score
94.2%
High Performers (80%+)
7

Performance Metrics

Max Context Window
144.4K
Avg Throughput
115.5 tok/s
Avg Latency
1ms
+
+
+
+
All Benchmark Results for GPT-4o
Complete list of benchmark scores with detailed information
AI2D
multimodal
0.94
94.2%
Self-reported
DocVQA
multimodal
0.93
92.8%
Self-reported
ChartQA
multimodal
0.86
85.7%
Self-reported
MMLU
text
0.86
85.7%
Self-reported
CharXiv-D
multimodal
0.85
85.3%
Self-reported
MMMLU
text
0.81
81.4%
Self-reported
IFEval
text
0.81
81.0%
Self-reported
MMLU-Pro
text
0.75
74.7%
Self-reported
MMMU
multimodal
0.72
72.2%
Self-reported
EgoSchema
video
0.72
72.2%
Self-reported
Showing 1 to 10 of 39 benchmarks
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+