Claude Opus 4.7

Leaderboards

Where Claude Opus 4.7 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 Claude Opus 4.7 has a published result on, out of 100%, with its rank among the models that took it.

• GPQA

  #5 / 256

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

  94.2%

  Verified

• SWE-Bench Verified

  #5 / 120

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

  87.6%

  Self-reported

• Humanity's Last Exam

  #15 / 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

  54.7%

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

• BrowseComp

  #21 / 68

  Finding hard-to-locate facts by browsing the web.

  79.3%

  Self-reported · In the agents score

• SWE-Bench Pro

  #11 / 61

  Harder, longer software engineering tasks from real codebases.

  64.3%

  Self-reported · In the coding score

• CharXiv-R

  #3 / 60

  Reading and reasoning about charts from scientific papers.

  91.0%

  Self-reported

• Terminal-Bench 2.0

  #10 / 54

  Getting real work done in a command-line terminal.

  69.4%

  Self-reported

• MMMLU

  #5 / 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.

  91.5%

  Self-reported

• Multi-Challenge

  #24 / 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.

  46.6%

  Verified

• LiveBench

  #8 / 38

  LiveBench is a challenging, contamination-limited LLM benchmark that addresses test set contamination by releasing new questions monthly based on recently-released datasets, arXiv papers, news articles, and IMDb movie synopses. It comprises tasks across math, coding, reasoning, language, instruction following, and data analysis with verifiable, objective ground-truth answers.

  76.9%

  Self-reported · In the text score

• MCP Atlas

  #11 / 38

  MCP Atlas is a benchmark for evaluating AI models on scaled tool use capabilities, measuring how well models can coordinate and utilize multiple tools across complex multi-step tasks.

  77.3%

  Self-reported

• Finance Agent v2

  #8 / 28

  Finance Agent v2 is an agentic financial-analysis benchmark from Vals that evaluates models on real-world finance workflows, measuring their ability to retrieve and reason over financial documents, perform multi-step calculations, and produce accurate analyses.

  51.5%

  Self-reported

• OSWorld-Verified

  #14 / 28

  OSWorld-Verified is a verified subset of OSWorld, a scalable real computer environment for multimodal agents supporting task setup, execution-based evaluation, and interactive learning across Ubuntu, Windows, and macOS.

  78.0%

  Self-reported

• HealthBench Hard

  #10 / 24

  A challenging variation of HealthBench that evaluates large language models' performance and safety in healthcare through 5,000 multi-turn conversations with particularly rigorous evaluation criteria validated by 262 physicians from 60 countries

  25.6%

  Verified

• LongBench v2

  #16 / 24

  LongBench v2 is a benchmark designed to assess the ability of LLMs to handle long-context problems requiring deep understanding and reasoning across real-world multitasks. It consists of 503 challenging multiple-choice questions with contexts ranging from 8k to 2M words across six major task categories: single-document QA, multi-document QA, long in-context learning, long-dialogue history understanding, code repository understanding, and long structured data understanding.

  53.9%

  Verified

• FrontierCode 1.1

  #18 / 23

  FrontierCode 1.1 evaluates whether coding-agent changes are mergeable, using unit tests, maintainer-defined rubrics, and verifiers. Runs flagged for unfair internet use receive a zero score.

  38.5%

  Self-reported · In the coding score

• CyberGym

  #17 / 21

  CyberGym is a benchmark for evaluating AI agents on cybersecurity tasks, testing their ability to identify vulnerabilities, perform security analysis, and complete security-related challenges in a controlled environment.

  73.1%

  Self-reported

• FrontierSWE

  #8 / 16

  FrontierSWE measures whether an agent can complete open-ended technical projects at the scale of hours to tens of hours, spanning systems optimization, large-scale code construction, and applied ML research. Performance is reported as a dominance score, where higher is better.

  63.0%

  Self-reported

• Legal Agent Benchmark

  #5 / 15

  The Legal Agent Benchmark (LAB) is Harvey's open-source benchmark for evaluating AI agents on complex, long-horizon legal work. Tasks are scored under an all-pass standard against expert-curated rubrics, where a task passes only if every required rubric criterion (facts, conclusions, citations, structure, and analytical moves) passes.

  7.1%

  Self-reported

• HealthBench (hard)

  #3 / 13

  25.6%

  Unverified

• GPQA (diamond)

  #3 / 10

  Graduate-level Google-Proof Q&A benchmark with paper-aligned full and diamond subsets.

  87.9%

  Unverified

• MultiChallenge (default)

  #4 / 9

  46.6%

  Unverified

• Finance Agent

  #1 / 8

  Finance Agent is a benchmark for evaluating AI models on agentic financial analysis tasks, testing their ability to process financial data, perform calculations, and generate accurate analyses across various financial domains.

  64.4%

  Self-reported

• LongBench-V2 (short)

  #3 / 6

  53.9%

  Unverified

• nolima (hard_16k)

  #2 / 6

  83.5%

  Independent