GPT-5 nano
Multimodal
Zero-eval
by OpenAI
+
+
+
+
About
GPT-5 nano is a multimodal language model developed by OpenAI. The model shows competitive results across 5 benchmarks. It excels particularly in AIME 2025 (85.2%), HMMT 2025 (75.6%), GPQA (71.2%). It supports a 528K 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 2025, it represents OpenAI's latest advancement in AI technology.
+
+
+
+
Pricing Range
Input (per 1M)$0.05 -$0.05
Output (per 1M)$0.40 -$0.40
Providers2
+
+
+
+
Timeline
AnnouncedAug 7, 2025
ReleasedAug 7, 2025
Knowledge CutoffMay 30, 2024
+
+
+
+
Specifications
Capabilities
Multimodal
+
+
+
+
License & Family
License
Proprietary
Performance Overview
Performance metrics and category breakdown
Overall Performance
5 benchmarks
Average Score
50.1%
Best Score
85.2%
High Performers (80%+)
1Performance Metrics
Max Context Window
528.0KAvg Throughput
500.0 tok/sAvg Latency
0ms+
+
+
+
All Benchmark Results for GPT-5 nano
Complete list of benchmark scores with detailed information
| AIME 2025 | text | 0.85 | 85.2% | Self-reported | |
| HMMT 2025 | text | 0.76 | 75.6% | Self-reported | |
| GPQA | text | 0.71 | 71.2% | Self-reported | |
| FrontierMath | text | 0.10 | 9.6% | Self-reported | |
| Humanity's Last Exam | multimodal | 0.09 | 8.7% | Self-reported |