OpenAI

GPT-5

Multimodal
Zero-eval
#1SWE-Lancer (IC-Diamond subset)
#1COLLIE
#1Tau2 Telecom
+30 more

by OpenAI

+
+
+
+
About

GPT-5 represents the next generation of OpenAI's foundational models, developed to advance the frontier of AI capabilities in reasoning, knowledge, and general intelligence. Built to push beyond the limitations of GPT-4, it incorporates architectural and training improvements designed to enhance performance across diverse tasks and domains.

+
+
+
+
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%+)
19

Performance Metrics

Max Context Window
528.0K
Avg Throughput
100.0 tok/s
Avg 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
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+