GPT is OpenAI's model family/series for language-oriented text and code tasks, with OpenAI API releases including GPT-5.6 Sol, GPT-5.5, GPT-5.4, GPT-5, GPT-4.1, GPT-4o, GPT-4 Turbo, GPT-4, and GPT-3.5 Turbo.
Pricing
Model profile · Current snapshot
Input / 1M
$1.25
Output / 1M
$10.00
Blended / 1M
$3.44
Output TPS
119
TTFT (s)
93.11
Model Intelligence
Arena ranking
36
Benchmarkable
No
Model level
family
Intelligence Index
36.1
Math Index
94.3
MMLU Pro
0.87
GPQA
0.85
HLE
0.27
LiveCodeBench
0.85
SciCode
0.43
MATH-500
0.99
AIME
0.96
AIME 2025
0.94
IFBench
0.73
LCR
0.76
TerminalBench Hard
0.33
TAU2
0.85
Recent stories
2 linked stories
newsSECONDARY2026-07-17
Kimi K3 benchmarks question cost advantage as token use rises
Illscience found Kimi K3 strong on prose reasoning but costly per task because it used more tokens than expected. LLMJunky's Rocket League-style test said the model made good UI but lacked Fable-level polish.
releasePRIMARY2026-04-23
OpenAI releases GPT-5.5 in ChatGPT and Codex for tool use
OpenAI launched GPT-5.5 in ChatGPT and Codex for coding, computer use, docs, sheets, and longer tool-driven tasks. Early tests showed stronger games and frontend builds, while pricing jumped again and Opus 4.7 comparisons started immediately.