mlsanityData to 7 Oct 2026

OpenAI GPT-5 System Card

arXiv 2601.03267 ↗First posted 19 Dec 2025cs.CL cs.AIcited by 910

Not on the map. Why?

Cited by 298 in LLM reasoning, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

This is the system card published alongside the OpenAI GPT-5 launch, August 2025. GPT-5 is a unified system with a smart and fast model that answers most questions, a deeper reasoning model for harder problems, and a real-time router that quickly decides which model to use based on conversation type, complexity, tool needs, and explicit intent (for example, if you say 'think hard about this' in the prompt). The router is continuously trained on real signals, including when users switch models, preference rates for responses, and measured correctness, improving over time. Once usage limits are reached, a mini version of each model handles remaining queries. This system card focuses primarily on gpt-5-thinking and gpt-5-main, while evaluations for other models are available in the appendix. The GPT-5 system not only outperforms previous models on benchmarks and answers questions more quickly, but -- more importantly -- is more useful for real-world queries. We've made significant advances in reducing hallucinations, improving instruction following, and minimizing sycophancy, and have leveled up GPT-5's performance in three of ChatGPT's most common uses: writing, coding, and health. All of the GPT-5 models additionally feature safe-completions, our latest approach to safety training to prevent disallowed content. Similarly to ChatGPT agent, we have decided to treat gpt-5-thinking as High capability in the Biological and Chemical domain under our Preparedness Framework, activating the associated safeguards. While we do not have definitive evidence that this model could meaningfully help a novice to create severe biological harm -- our defined threshold for High capability -- we have chosen to take a precautionary approach.

Key facts. Cited by 910 papers in the map (data through 7 Oct 2026). First posted on arXiv 19 Dec 2025.

Builds on

0 of 0 references.

No references here yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 2; 2026: 908.

910 papers.

Sort:

By area:

  1. 2026CoEvoSkills: Self-Evolving Agent Skills via Co-Evolutionary Verificationcited by 117
  2. 2026Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?cited by 87
  3. 2026Vision-OPD: Learning to See Fine Details for Multimodal LLMs via On-Policy Self-Distillationcited by 71
  4. 2026MiniCPM-o 4.5: Towards Real-Time Full-Duplex Omni-Modal Interactioncited by 64
  5. 2026MIRAGE: The Illusion of Visual Understandingcited by 57
  6. 2026Graph-of-Skills: Dependency-Aware Structural Retrieval for Massive Agent Skillscited by 53
  7. 2026Video-MME-v2: Towards the Next Stage in Benchmarks for Comprehensive Video Understandingcited by 46
  8. 2026MolmoAct2: Action Reasoning Models for Real-world Deploymentcited by 45
  9. 2026REDSearcher: A Scalable and Cost-Efficient Framework for Long-Horizon Search Agentscited by 43
  10. 2026MOVA: Towards Scalable and Synchronized Video-Audio Generationcited by 39
  11. 2026Vision-DeepResearch: Incentivizing DeepResearch Capability in Multimodal Large Language Modelscited by 33
  12. 2026Video-OPD: Efficient Post-Training of Multimodal Large Language Models for Temporal Video Grounding via On-Policy Distillationcited by 32
38 more
  1. 2026Group-Evolving Agents: Open-Ended Self-Improvement via Experience Sharingcited by 32
  2. 2026OpenSeeker: Democratizing Frontier Search Agents by Fully Open-Sourcing Training Datacited by 32
  3. 2026Vision-DeepResearch Benchmark: Rethinking Visual and Textual Search for Multimodal Large Language Modelscited by 30
  4. 2026Lightning OPD: Efficient Post-Training for Large Reasoning Models with Offline On-Policy Distillationcited by 28
  5. 2026SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecturecited by 27
  6. 2026ClawGuard: A Runtime Security Framework for Tool-Augmented LLM Agents Against Indirect Prompt Injectioncited by 25
  7. 2026ContextBench: A Benchmark for Context Retrieval in Coding Agentscited by 23
  8. 2026CLI-Gym: Scalable CLI Task Generation via Agentic Environment Inversioncited by 20
  9. 2026Evaluating AGENTS.md: Are Repository-Level Context Files Helpful for Coding Agents?cited by 19
  10. 2026OpenSearch-VL: An Open Recipe for Frontier Multimodal Search Agentscited by 18
  11. 2026UniDriveVLA: Unifying Understanding, Perception, and Action Planning for Autonomous Drivingcited by 17
  12. 2026RetroAgent: From Solving to Evolving via Retrospective Dual Intrinsic Feedbackcited by 16
  13. 2026AI-Assisted Peer Review at Scale: The AAAI-26 AI Review Pilotcited by 15
  14. 2026Qwen-Scope: Turning Sparse Features into Development Tools for Large Language Modelscited by 15
  15. 2026VIBEVOICE-ASR Technical Reportcited by 14
  16. 2026CoopEval: Benchmarking Cooperation-Sustaining Mechanisms and LLM Agents in Social Dilemmascited by 14
  17. 2026OGLS-SD: On-Policy Self-Distillation with Outcome-Guided Logit Steering for LLM Reasoningcited by 14
  18. 2026HunyuanOCR-1.5: Making Lightweight OCR VLMs Faster and Bettercited by 14
  19. 2026Position: Agentic Evolution is the Path to Evolving LLMscited by 13
  20. 2026When Benign Inputs Lead to Severe Harms: Eliciting Unsafe Unintended Behaviors of Computer-Use Agentscited by 13
  21. 2026PISmith: Reinforcement Learning-based Red Teaming for Prompt Injection Defensescited by 13
  22. 2026Learning Query-Aware Budget-Tier Routing for Runtime Agent Memorycited by 12
  23. 2026Evaluating Memory Structure in LLM Agentscited by 12
  24. 2026Memory in the LLM Era: Modular Architectures and Strategies in a Unified Frameworkcited by 12
  25. 2026Are VLMs Seeing or Just Saying? Uncovering the Illusion of Visual Re-examinationcited by 12
  26. 2026MemTX: Transactional Belief Commit for Stateful Agent Memorycited by 12
  27. 2026Computer Environments Elicit General Agentic Intelligence in LLMscited by 11
  28. 2026Agent Primitives: Reusable Latent Building Blocks for Multi-Agent Systemscited by 11
  29. 2026Coding Agents are Effective Long-Context Processorscited by 11
  30. 2026ECHO: Elastic Speculative Decoding with Sparse Gating for High-Concurrency Scenarioscited by 11
  31. 2026Baichuan-M3: Modeling Clinical Inquiry for Reliable Medical Decision-Makingcited by 10
  32. 2026AndroTMem: From Interaction Trajectories to Anchored Memory in Long-Horizon GUI Agentscited by 10
  33. 2026AIRA_2: Overcoming Bottlenecks in AI Research Agentscited by 10
  34. 2026Vero: An Open RL Recipe for General Visual Reasoningcited by 10
  35. 2026Quantized Reasoning Models Think They Need to Think Longer, but They Do Notcited by 10
  36. 2026ProjDevBench: Benchmarking AI Coding Agents on End-to-End Project Developmentcited by 9
  37. 2026DSDR: Dual-Scale Diversity Regularization for Exploration in LLM Reasoningcited by 9
  38. 2026RubiCap: Rubric-Guided Reinforcement Learning for Dense Image Captioningcited by 9

50 most cited of 910 All 910 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025gpt-oss-120b & gpt-oss-20b Model Card
  2. 2025Performance of GPT-5 Frontier Models in Ophthalmology Question Answering
  3. 2025Is GPT-OSS Good? A Comprehensive Evaluation of OpenAI's Latest Open Source Models
  4. 2025GPT-OSS-20B: A Comprehensive Deployment-Centric Analysis of OpenAI's Open-Weight Mixture of Experts Model
  5. 2024System 2 thinking in OpenAI's o1-preview model: Near-perfect performance on a mathematics exam
  6. 20261GC-7RC: One Graphic Card -- Seven Research Challenges! How Good Are AI Agents at Doing Your Job?
  7. 2023Performance of ChatGPT on USMLE: Unlocking the Potential of Large Language Models for AI-Assisted Medical Education
  8. 2025Quant Fever, Reasoning Blackholes, Schrodinger's Compliance, and More: Probing GPT-OSS-20B