AI Model Timeline

Tracking the accelerating release frequency of frontier AI models.

ChatGPT

OpenAI·

LLMsflagshipcloud

Overview

Chat interface for GPT-3.5 that took the world by storm.

Capabilities and innovations

Conversational interfaceRLHF tuningBroad general knowledgeRLHF AlignmentConversational InterfaceHuman Preference Learning

Benchmarks

BenchmarkScoreSource
GPQA Diamond28%unsourced
Humanity’s Last Exam (no tools)2%vendor
Reported as "< 2%", stored as upper bound 2.0
SWE-bench Verified3.2%unsourced
MMLU70%unsourced
  • SWE-bench Pro: benchmark did not exist at release
  • MMLU-Pro: benchmark did not exist at release
  • Terminal-Bench 2.x: benchmark did not exist at release
  • MMMU-Pro: benchmark did not exist at release

Links

More from OpenAI

Data curated by AI Model Timeline. See the methodology for admission criteria, benchmark eras and source priority.