GPT-4.1 mini

Leaderboards

Where GPT-4.1 mini sits among the top 20 in each category.

By task

Scored from votes on each kind of prompt alone, on the same 1,000-point scale.

Test results

Every test GPT-4.1 mini has a published result on, out of 100%, with its rank among the models that took it.

• GPQA

  #171 / 256

  Graduate-level science questions written to be hard to look up.

  65.0%

  Self-reported

• AIME 2025

  #118 / 123

  Competition maths problems from the 2025 American Invitational Mathematics Exam.

  40.2%

  Self-reported

• SWE-Bench Verified

  #117 / 120

  Fixing real bugs in real GitHub projects, checked by the projects' own tests.

  23.6%

  Self-reported

• Humanity's Last Exam

  #108 / 108

  Humanity's Last Exam (HLE) is a multi-modal academic benchmark with 2,500 questions across mathematics, humanities, and natural sciences, designed to test LLM capabilities at the frontier of human knowledge with unambiguous, verifiable solutions

  3.7%

  Self-reported · In the text score· In the vision score

• MMLU

  #24 / 103

  Massive Multitask Language Understanding benchmark testing knowledge across 57 diverse subjects including STEM, humanities, social sciences, and professional domains

  87.5%

  Self-reported

• IFEval

  #44 / 70

  Instruction-Following Evaluation (IFEval) benchmark for large language models, focusing on verifiable instructions with 25 types of instructions and around 500 prompts containing one or more verifiable constraints

  84.1%

  Self-reported

• MMMU

  #30 / 66

  MMMU (Massive Multi-discipline Multimodal Understanding) is a benchmark designed to evaluate multimodal models on college-level subject knowledge and deliberate reasoning. Contains 11.5K meticulously collected multimodal questions from college exams, quizzes, and textbooks, covering six core disciplines: Art & Design, Business, Science, Health & Medicine, Humanities & Social Science, and Tech & Engineering across 30 subjects and 183 subfields.

  72.7%

  Self-reported

• CharXiv-R

  #50 / 60

  Reading and reasoning about charts from scientific papers.

  56.8%

  Self-reported

• AIME 2024

  #48 / 54

  American Invitational Mathematics Examination 2024, consisting of 30 challenging mathematical reasoning problems from AIME I and AIME II competitions. Each problem requires an integer answer between 0-999 and tests advanced mathematical reasoning across algebra, geometry, combinatorics, and number theory. Used as a benchmark for evaluating mathematical reasoning capabilities in large language models at Olympiad-level difficulty.

  49.6%

  Self-reported

• MMMLU

  #42 / 51

  Multilingual Massive Multitask Language Understanding dataset released by OpenAI, featuring professionally translated MMLU test questions across 14 languages including Arabic, Bengali, German, Spanish, French, Hindi, Indonesian, Italian, Japanese, Korean, Portuguese, Swahili, Yoruba, and Chinese. Contains approximately 15,908 multiple-choice questions per language covering 57 subjects.

  78.5%

  Self-reported

• Multi-Challenge

  #36 / 41

  MultiChallenge is a realistic multi-turn conversation evaluation benchmark that challenges frontier LLMs across four key categories: instruction retention (maintaining instructions throughout conversations), inference memory (recalling and connecting details from previous turns), reliable versioned editing (adapting to evolving instructions during collaborative editing), and self-coherence (avoiding contradictions in responses). The benchmark evaluates models on sustained, contextually complex dialogues across diverse topics including travel planning, technical documentation, and professional communication.

  35.8%

  Self-reported

• MathVista

  #10 / 40

  MathVista evaluates mathematical reasoning of foundation models in visual contexts. It consists of 6,141 examples derived from 28 existing multimodal datasets and 3 newly created datasets (IQTest, FunctionQA, and PaperQA), combining challenges from diverse mathematical and visual tasks to assess models' ability to understand complex figures and perform rigorous reasoning.

  73.1%

  Self-reported

• HMMT 2025

  #31 / 33

  Harvard-MIT Mathematics Tournament 2025 - A prestigious student-organized mathematics competition for high school students featuring two tournaments (November 2025 at MIT and February 2026 at Harvard) with individual tests, team rounds, and guts rounds

  35.0%

  Self-reported

• Multi-IF

  #20 / 25

  Multi-IF benchmarks LLMs on multi-turn and multilingual instruction following. It expands upon IFEval by incorporating multi-turn sequences and translating English prompts into 7 other languages, resulting in 4,501 multilingual conversations with three turns each. The benchmark reveals that current leading LLMs struggle with maintaining accuracy in multi-turn instructions and shows higher error rates for non-Latin script languages.

  67.0%

  Self-reported

• TAU-bench Retail

  #22 / 25

  A benchmark for evaluating tool-agent-user interaction in retail environments. Tests language agents' ability to handle dynamic conversations with users while using domain-specific API tools and following policy guidelines. Evaluates agents on tasks like order cancellations, address changes, and order status checks through multi-turn conversations.

  55.8%

  Self-reported

• TAU-bench Airline

  #20 / 23

  Part of τ-bench (TAU-bench), a benchmark for Tool-Agent-User interaction in real-world domains. The airline domain evaluates language agents' ability to interact with users through dynamic conversations while following domain-specific rules and using API tools. Agents must handle airline-related tasks and policies reliably.

  36.0%

  Self-reported

• Aider-Polyglot

  #19 / 22

  A coding benchmark that evaluates LLMs on 225 challenging Exercism programming exercises across C++, Go, Java, JavaScript, Python, and Rust. Models receive two attempts to solve each problem, with test error feedback provided after the first attempt if it fails. The benchmark measures both initial problem-solving ability and capacity to edit code based on error feedback, providing an end-to-end evaluation of code generation and editing capabilities across multiple programming languages.

  34.7%

  Self-reported

• CharXiv-D

  #7 / 18

  CharXiv-D is the descriptive questions subset of the CharXiv benchmark, designed to assess multimodal large language models' ability to extract basic information from scientific charts. It contains descriptive questions covering information extraction, enumeration, pattern recognition, and counting across 2,323 diverse charts from arXiv papers, all curated and verified by human experts.

  88.4%

  Self-reported

• Graphwalks BFS <128k

  #9 / 13

  A graph reasoning benchmark that evaluates language models' ability to perform breadth-first search (BFS) operations on graphs with context length under 128k tokens, returning nodes reachable at specified depths.

  61.7%

  Self-reported

• Graphwalks BFS >128k

  #11 / 12

  A graph reasoning benchmark that evaluates language models' ability to perform breadth-first search (BFS) operations on graphs with context length over 128k tokens, testing long-context reasoning capabilities.

  15.0%

  Self-reported

• Graphwalks parents <128k

  #7 / 12

  A graph reasoning benchmark that evaluates language models' ability to find parent nodes in graphs with context length under 128k tokens, requiring understanding of graph structure and edge relationships.

  60.5%

  Self-reported

• COLLIE

  #10 / 11

  COLLIE is a grammar-based framework for systematic construction of constrained text generation tasks. It allows specification of rich, compositional constraints across diverse generation levels and modeling challenges including language understanding, logical reasoning, and semantic planning. The COLLIE-v1 dataset contains 2,080 instances across 13 constraint structures.

  54.6%

  Self-reported

• Aider-Polyglot Edit

  #8 / 10

  A challenging multi-language coding benchmark that evaluates models' code editing abilities across C++, Go, Java, JavaScript, Python, and Rust. Contains 225 of Exercism's most difficult programming problems, selected as problems that were solved by 3 or fewer out of 7 top coding models. The benchmark focuses on code editing tasks and measures both correctness of solutions and proper edit format usage. Designed to re-calibrate evaluation scales so top models score between 5-50%.

  31.6%

  Self-reported

• OpenAI-MRCR: 2 needle 128k

  #5 / 9

  Multi-round Co-reference Resolution (MRCR) benchmark for evaluating an LLM's ability to distinguish between multiple needles hidden in long context. Models are given a long, multi-turn synthetic conversation and must retrieve a specific instance of a repeated request, requiring reasoning and disambiguation skills beyond simple retrieval.

  47.2%

  Self-reported

• ComplexFuncBench

  #5 / 7

  ComplexFuncBench is a benchmark designed to evaluate large language models' capabilities in handling complex function calling scenarios. It encompasses multi-step and constrained function calling tasks that require long-parameter filling, parameter value reasoning, and managing contexts up to 128k tokens. The benchmark includes 1,000 samples across five real-world scenarios.

  49.3%

  Self-reported

• Graphwalks parents >128k

  #6 / 7

  A graph reasoning benchmark that evaluates language models' ability to find parent nodes in graphs with context length over 128k tokens, testing long-context reasoning and graph structure understanding.

  11.0%

  Self-reported

• Internal API instruction following (hard)

  #5 / 7

  Internal API instruction following (hard) benchmark - specific documentation not found in official sources

  45.1%

  Self-reported

• OpenAI-MRCR: 2 needle 1M

  #4 / 5

  Multi-Round Co-reference Resolution benchmark that tests an LLM's ability to distinguish between multiple similar needles hidden in long conversations. Models must reproduce specific instances of content (e.g., 'Return the 2nd poem about tapirs') from multi-turn synthetic conversations, requiring reasoning about context, ordering, and subtle differences between similar outputs.

  33.3%

  Self-reported