GPT-5

The builder’s guide to GPT‑5.6

Now in preview: The ChatGPT desktop app for Linux. Use ChatGPT, ChatGPT Work, and Codex where you already work and build, with your projects and browser workflows on supported Linux systems. https://t

Now in preview: The ChatGPT desktop app for Linux. Use ChatGPT, ChatGPT Work, and Codex where you already work and build, with your projects and browser workflows on supported Linux systems. https://t.co/OtsPt5N5QC

Testing ads in ChatGPT

Daybreak models are now available on AWS

Putting frontier cyber models in more trusted hands

How Zapier transformed core marketing processes with ChatGPT Work

Virgin Atlantic sharpens customer journeys with ChatGPT Work

Premium seats are coming to ChatGPT Business

Soohak: A Mathematician-Curated Benchmark for Evaluating Research-level Math Capabilities of LLMs

Following the recent achievement of gold-medal performance on the IMO by frontier LLMs, the community is searching for the next meaningful and challenging target for measuring LLM reasoning. Whereas olympiad-style problems measure step-by-step reasoning alone, research-level problems use such reasoning to advance the frontier of mathematical knowledge itself, emerging as a compelling alternative. Yet research-level math benchmarks remain scarce because such problems are difficult to source (e.g., Riemann Bench and FrontierMath-Tier 4 contain 25 and 50 problems, respectively). To support reliable evaluation of next-generation frontier models, we introduce Soohak, a 439-problem benchmark newly authored from scratch by 64 mathematicians. Soohak comprises two subsets. On the Challenge subset, frontier models including Gemini-3-Pro, GPT-5, and Claude-Opus-4.5 reach 30.4%, 26.4%, and 10.4% respectively, leaving substantial headroom, while leading open-weight models such as Qwen3-235B, GPT-OSS-120B, and Kimi-2.5 remain below 15%. Notably, beyond standard problem solving, Soohak introduces a refusal subset that probes a capability intrinsic to research mathematics: recognizing ill-posed problems and pausing rather than producing confident but unjustified answers. On this subset, no model exceeds 50%, identifying refusal as a new optimization target that current models do not directly address. To prevent contamination, the dataset will be publicly released in late 2026, with model evaluations available upon request in the interim.

RewardHarness: Self-Evolving Agentic Post-Training

Evaluating instruction-guided image edits requires rewards that reflect subtle human preferences, yet current reward models typically depend on large-scale preference annotation and additional model training. This creates a data-efficiency gap: humans can often infer the target evaluation criteria from only a few examples, while models are usually trained on hundreds of thousands of comparisons. We present RewardHarness, a self-evolving agentic reward framework that reframes reward modeling as context evolution rather than weight optimization. Instead of learning from large-scale annotations, RewardHarness aligns with human preferences by iteratively evolving a library of tools and skills from as few as 100 preference demonstrations. Given a source image, candidate edited images, and an editing instruction, an Orchestrator selects the most relevant subset of tools and skills from the maintained library, and a frozen Sub-Agent uses them to construct a reasoning chain that produces a preference judgment. By comparing predicted judgments with ground-truth preferences and analyzing successes and failures in the reasoning process, the Orchestrator automatically refines its library of tools and skills without additional human annotation. Using only 0.05% of the EditReward preference data, RewardHarness achieves 47.4% average accuracy on image-editing evaluation benchmarks, surpassing GPT-5 by 5.3 points. When used as a reward signal for GRPO fine-tuning, RL-tuned models achieve 3.52 on ImgEdit-Bench. Project page: https://rewardharness.com.

SketchVLM: Vision language models can annotate images to explain thoughts and guide users

When answering questions about images, humans naturally point, label, and draw to explain their reasoning. In contrast, modern vision-language models (VLMs) such as Gemini-3-Pro and GPT-5 only respond with text, which can be difficult for users to verify. We present SketchVLM, a training-free, model-agnostic framework that enables VLMs to produce non-destructive, editable SVG overlays on the input image to visually explain their answers. Across seven benchmarks spanning visual reasoning (maze navigation, ball-drop trajectory prediction, and object counting) and drawing (part labeling, connecting-the-dots, and drawing shapes around objects), SketchVLM improves visual reasoning task accuracy by up to +28.5 percentage points and annotation quality by up to 1.48x relative to image-editing and fine-tuned sketching baselines, while also producing annotations that are more faithful to the model's stated answer. We find that single-turn generation already achieves strong accuracy and annotation quality, and multi-turn generation opens up further opportunities for human-AI collaboration. An interactive demo and code are at https://sketchvlm.github.io/.

ImplicitMemBench: Measuring Unconscious Behavioral Adaptation in Large Language Models

Existing memory benchmarks for LLM agents evaluate explicit recall of facts, yet overlook implicit memory where experience becomes automated behavior without conscious retrieval. This gap is critical: effective assistants must automatically apply learned procedures or avoid failed actions without explicit reminders. We introduce ImplicitMemBench, the first systematic benchmark evaluating implicit memory through three cognitively grounded constructs drawn from standard cognitive-science accounts of non-declarative memory: Procedural Memory (one-shot skill acquisition after interference), Priming (theme-driven bias via paired experimental/control instances), and Classical Conditioning (Conditioned Stimulus--Unconditioned Stimulus (CS--US) associations shaping first decisions). Our 300-item suite employs a unified Learning/Priming-Interfere-Test protocol with first-attempt scoring. Evaluation of 17 models reveals severe limitations: no model exceeds 66% overall, with top performers DeepSeek-R1 (65.3%), Qwen3-32B (64.1%), and GPT-5 (63.0%) far below human baselines. Analysis uncovers dramatic asymmetries (inhibition 17.6% vs. preference 75.0%) and universal bottlenecks requiring architectural innovations beyond parameter scaling. ImplicitMemBench reframes evaluation from "what agents recall" to "what they automatically enact".

Introducing GPT‑5 for developers

Introducing GPT‑5 for developers | OpenAI Skip to main content Research Products Business Developers Company Foundation (opens in a new window) Log in Try ChatGPT (opens in a new window) Research Products Business Developers Company Foundation (opens in a new window) Try ChatGPT (opens in a new window) Login OpenAI August 7, 2025 Product Introducing GPT‑5 for developers The best model for coding and agentic tasks. Loading… Share Introduction Introduction Coding Frontend engin

GPT-5.6: Frontier intelligence that scales with your ambition

GPT-5.6: Frontier intelligence that scales with your ambition | OpenAI Skip to main content Research Products Business Developers Company Foundation (opens in a new window) Log in Try ChatGPT (opens in a new window) Research Products Business Developers Company Foundation (opens in a new window) Try ChatGPT (opens in a new window) Login OpenAI July 9, 2026 Product Release GPT‑5.6: Frontier intelligence that scales with your ambition More intelligence from every token, stronge

Introducing GPT-5.1 for developers

Introducing GPT-5.1 for developers | OpenAI Skip to main content Research Products Business Developers Company Foundation (opens in a new window) Log in Try ChatGPT (opens in a new window) Research Products Business Developers Company Foundation (opens in a new window) Try ChatGPT (opens in a new window) Login OpenAI November 13, 2025 Product Introducing GPT‑5.1 for developers Loading… Share Efficient reasoning across tasks Efficient reasoning across tasks Adaptive reasoning

Introducing GPT-5.2

Introducing GPT-5.2 | OpenAI Skip to main content Research Products Business Developers Company Foundation (opens in a new window) Log in Try ChatGPT (opens in a new window) Research Products Business Developers Company Foundation (opens in a new window) Try ChatGPT (opens in a new window) Login OpenAI December 11, 2025 Product Release Introducing GPT‑5.2 The most advanced frontier model for professional work and long-running agents. Loading… Share Model performance Model per

OpenAI Codex (GPT-5 family) - GAIA

GAIA score 11.6 from Codex web-assisted Level3 diagnostic

Models | OpenAI API

ChatGPT Home API Codex Docs Guides, concepts, and product docs for Codex Use cases Example workflows and tasks teams can take on with ChatGPT or Codex Docs Use cases Resources ChatGPT Plugins Extend ChatGPT and Codex Workspace Agents Trigger published ChatGPT workspace agents Commerce Build commerce flows in ChatGPT Ads Publish and measure ads in ChatGPT Resources Showcase Demo apps to get inspired Blog Learnings and experiences from developers Cookbook Notebook examples for

Models | OpenAI API

ChatGPT Home API Codex Docs Guides, concepts, and product docs for Codex Use cases Example workflows and tasks teams can take on with ChatGPT or Codex Docs Use cases Resources ChatGPT Plugins Extend ChatGPT and Codex Workspace Agents Trigger published ChatGPT workspace agents Commerce Build commerce flows in ChatGPT Ads Publish and measure ads in ChatGPT Resources Showcase Demo apps to get inspired Blog Learnings and experiences from developers Cookbook Notebook examples for

Models | OpenAI API

ChatGPT Home API Codex Docs Guides, concepts, and product docs for Codex Use cases Example workflows and tasks teams can take on with ChatGPT or Codex Docs Use cases Resources ChatGPT Plugins Extend ChatGPT and Codex Workspace Agents Trigger published ChatGPT workspace agents Commerce Build commerce flows in ChatGPT Ads Publish and measure ads in ChatGPT Resources Showcase Demo apps to get inspired Blog Learnings and experiences from developers Cookbook Notebook examples for

Models | OpenAI API

ChatGPT Home API Codex Docs Guides, concepts, and product docs for Codex Use cases Example workflows and tasks teams can take on with ChatGPT or Codex Docs Use cases Resources ChatGPT Plugins Extend ChatGPT and Codex Workspace Agents Trigger published ChatGPT workspace agents Commerce Build commerce flows in ChatGPT Ads Publish and measure ads in ChatGPT Resources Showcase Demo apps to get inspired Blog Learnings and experiences from developers Cookbook Notebook examples for

Models | OpenAI API

Models | OpenAI API Home API Docs Guides and concepts for the OpenAI API API reference Endpoints, parameters, and responses Codex Docs Guides, concepts, and product docs for Codex Use cases Example workflows and tasks teams hand to Codex ChatGPT Apps SDK Build apps to extend ChatGPT Commerce Build commerce flows in ChatGPT Ads Publish and measure ads in ChatGPT Resources Showcase Demo apps to get inspired Blog Learnings and experiences from developers Cookbook Notebook exampl

GPT-5.3 Instant benchmark update

OpenAI published official provider-reported benchmark evidence for GPT-5.3, GPT-5.3 Instant, gpt-5.3-instant, GPT-5.3 Chat.