GPT-4o mini
Multimodal
Zero-eval
by OpenAI
+
+
+
+
About
GPT-4o mini is a multimodal language model developed by OpenAI. It achieves strong performance with an average score of 63.5% across 9 benchmarks. It excels particularly in HumanEval (87.2%), MGSM (87.0%), MMLU (82.0%). It supports a 144K token context window for handling large documents. The model is available through 1 API provider. 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)$0.15 -$0.15
Output (per 1M)$0.60 -$0.60
Providers1
+
+
+
+
Timeline
AnnouncedJul 18, 2024
ReleasedJul 18, 2024
Knowledge CutoffOct 1, 2023
+
+
+
+
Specifications
Capabilities
Multimodal
+
+
+
+
License & Family
License
Proprietary
Performance Overview
Performance metrics and category breakdown
Overall Performance
9 benchmarks
Average Score
63.5%
Best Score
87.2%
High Performers (80%+)
3Performance Metrics
Max Context Window
144.4KAvg Throughput
92.0 tok/sAvg Latency
1ms+
+
+
+
All Benchmark Results for GPT-4o mini
Complete list of benchmark scores with detailed information
| HumanEval | text | 0.87 | 87.2% | Self-reported | |
| MGSM | text | 0.87 | 87.0% | Self-reported | |
| MMLU | text | 0.82 | 82.0% | Self-reported | |
| DROP | text | 0.80 | 79.7% | Self-reported | |
| MATH | text | 0.70 | 70.2% | Self-reported | |
| MMMU | multimodal | 0.59 | 59.4% | Self-reported | |
| MathVista | multimodal | 0.57 | 56.7% | Self-reported | |
| GPQA | text | 0.40 | 40.2% | Self-reported | |
| SWE-Bench Verified | text | 0.09 | 8.7% | Self-reported |