GPT-5
Multimodal
Zero-eval
#1SWE-Lancer (IC-Diamond subset)
#1COLLIE
#1Tau2 Telecom
+30 more
by OpenAI
+
+
+
+
About
GPT-5 is a multimodal language model developed by OpenAI. It achieves strong performance with an average score of 70.1% across 35 benchmarks. It excels particularly in SWE-Lancer (IC-Diamond subset) (100.0%), COLLIE (99.0%), Tau2 Telecom (96.7%). 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)$1.25 -$1.25
Output (per 1M)$10.00 -$10.00
Providers2
+
+
+
+
Timeline
AnnouncedAug 7, 2025
ReleasedAug 7, 2025
Knowledge CutoffSep 30, 2024
+
+
+
+
Specifications
Capabilities
Multimodal
+
+
+
+
License & Family
License
Proprietary
Performance Overview
Performance metrics and category breakdown
Overall Performance
35 benchmarks
Average Score
70.1%
Best Score
100.0%
High Performers (80%+)
19Performance Metrics
Max Context Window
528.0KAvg Throughput
100.0 tok/sAvg Latency
2ms+
+
+
+
All Benchmark Results for GPT-5
Complete list of benchmark scores with detailed information
| SWE-Lancer (IC-Diamond subset) | text | 1.00 | 100.0% | Self-reported | |
| COLLIE | text | 0.99 | 99.0% | Self-reported | |
| Tau2 Telecom | text | 0.97 | 96.7% | Self-reported | |
| OpenAI-MRCR: 2 needle 128k | text | 0.95 | 95.2% | Self-reported | |
| AIME 2025 | text | 0.95 | 94.6% | Self-reported | |
| HumanEval | text | 0.93 | 93.4% | Self-reported | |
| HMMT 2025 | text | 0.93 | 93.3% | Self-reported | |
| MMLU | text | 0.93 | 92.5% | Self-reported | |
| BrowseComp Long Context 128k | text | 0.90 | 90.0% | Self-reported | |
| BrowseComp Long Context 256k | text | 0.89 | 88.8% | Self-reported |
Showing 1 to 10 of 35 benchmarks