Benchmarks and evaluation

Advancing science and math with GPT-5.2

GPT-5. 2 is OpenAI’s strongest model yet for math and science, setting new state-of-the-art results on benchmarks like GPQA Diamond and FrontierMath.

Introducing GPT-5.2

GPT-5. 2 is our most advanced frontier model for everyday professional work, with state-of-the-art reasoning, long-context understanding, coding, and vision.

FACTS Benchmark Suite: Systematically evaluating the factuality of large language models

Systematically evaluating the factuality of large language models with the FACTS Benchmark Suite.

Open ASR Leaderboard: Trends and Insights with New Multilingual & Long-Form Tracks

Introducing IndQA

OpenAI introduces IndQA, a new benchmark for evaluating AI systems in Indian languages. Built with domain experts, IndQA tests cultural understanding and reasoning across 12 languages and 10 knowledge areas.

RL without TD learning

In this post, I’ll introduce a reinforcement learning (RL) algorithm based on an “alternative” paradigm: divide and conquer . Unlike traditional methods, this algorithm is not based on temporal difference (TD) learning (which has scalability challenges ), and scales well to long-horizon tasks.

Addendum to GPT-5 System Card: Sensitive conversations

This system card details GPT-5’s improvements in handling sensitive conversations, including new benchmarks for emotional reliance, mental health, and jailbreak resistance.

Understanding the 4 Main Approaches to LLM Evaluation (From Scratch)

Multiple-Choice Benchmarks, Verifiers, Leaderboards, and LLM Judges with Code Examples

SOTA OCR with Core ML and dots.ocr

Launching Sora responsibly

To address the novel safety challenges posed by a state-of-the-art video model as well as a new social creation platform, we’ve built Sora 2 and the Sora app with safety at the foundation. Our approach is anchored in concrete protections.

What exactly does word2vec learn?

What exactly does word2vec learn, and how? Answering this question amounts to understanding representation learning in a minimal yet interesting language modeling task.

Introducing GPT-5

We are introducing GPT‑5, our best AI system yet. GPT‑5 is a significant leap in intelligence over all our previous models, featuring state-of-the-art performance across coding, math, writing, health, visual perception, and more.

Introducing gpt-oss

We’re releasing gpt-oss-120b and gpt-oss-20b—two state-of-the-art open-weight language models that deliver strong real-world performance at low cost. Available under the flexible Apache 2.

📚 3LM: A Benchmark for Arabic LLMs in STEM and Code

Ettin Suite: SoTA Paired Encoders and Decoders

Introducing HealthBench

HealthBench is a new evaluation benchmark for AI in healthcare which evaluates models in realistic scenarios. Built with input from 250+ physicians, it aims to provide a shared standard for model performance and safety in health.

OpenAI o3 and o4-mini System Card

OpenAI o3 and OpenAI o4-mini combine state-of-the-art reasoning with full tool capabilities—web browsing, Python, image and file analysis, image generation, canvas, automations, file search, and memory.

BrowseComp: a benchmark for browsing agents

BrowseComp: a benchmark for browsing agents.

PaperBench: Evaluating AI’s Ability to Replicate AI Research

We introduce PaperBench, a benchmark evaluating the ability of AI agents to replicate state-of-the-art AI research.

Introducing the SWE-Lancer benchmark

Can frontier LLMs earn $1 million from real-world freelance software engineering?