OpenAI

GPT-4 Turbo

Zero-eval

by OpenAI

+
+
+
+
About

GPT-4 Turbo was introduced as an optimized version of GPT-4, designed to provide enhanced performance with improved efficiency and an expanded context window. Built with updated knowledge and refined capabilities, it offered developers a more cost-effective way to leverage GPT-4's advanced reasoning while handling longer conversations and documents.

+
+
+
+
Pricing Range
Input (per 1M)$10.00 -$10.00
Output (per 1M)$30.00 -$30.00
Providers2
+
+
+
+
Timeline
AnnouncedApr 9, 2024
ReleasedApr 9, 2024
Knowledge CutoffDec 31, 2023
+
+
+
+
License & Family
License
Proprietary
Performance Overview
Performance metrics and category breakdown

Overall Performance

6 benchmarks
Average Score
78.1%
Best Score
88.5%
High Performers (80%+)
4

Performance Metrics

Max Context Window
132.1K
Avg Throughput
98.5 tok/s
Avg Latency
1ms
+
+
+
+
All Benchmark Results for GPT-4 Turbo
Complete list of benchmark scores with detailed information
MGSM
text
0.89
88.5%
Self-reported
HumanEval
text
0.87
87.1%
Self-reported
MMLU
text
0.86
86.5%
Self-reported
DROP
text
0.86
86.0%
Self-reported
MATH
text
0.73
72.6%
Self-reported
GPQA
text
0.48
48.0%
Self-reported
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+