Claude Opus 4.5

Leaderboards

Where Claude Opus 4.5 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 4.5 has a published result on, out of 100%, with its rank among the models that took it.

• GPQA

  #54 / 256

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

  87.0%

  Verified

• SWE-Bench Verified

  #7 / 120

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

  80.9%

  Self-reported

• Terminal-Bench 2.0

  #21 / 54

  Getting real work done in a command-line terminal.

  59.3%

  Self-reported

• MMMLU

  #7 / 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.

  90.8%

  Self-reported

• LiveBench

  #12 / 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.

  76.0%

  Self-reported · In the text score

• MCP Atlas

  #31 / 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.

  62.3%

  Self-reported

• Tau2 Telecom

  #5 / 36

  τ²-Bench telecom domain evaluates conversational agents in a dual-control environment modeled as a Dec-POMDP, where both agent and user use tools in shared telecommunications troubleshooting scenarios that test coordination and communication capabilities.

  98.2%

  Self-reported

• Tau2 Retail

  #3 / 27

  τ²-bench retail domain evaluates conversational AI agents in customer service scenarios within a dual-control environment where both agent and user can interact with tools. Tests tool-agent-user interaction, rule adherence, and task consistency in retail customer support contexts.

  88.9%

  Self-reported

• OSWorld

  #6 / 21

  OSWorld: The first-of-its-kind scalable, real computer environment for multimodal agents, supporting task setup, execution-based evaluation, and interactive learning across Ubuntu, Windows, and macOS with 369 computer tasks involving real web and desktop applications, OS file I/O, and multi-application workflows

  66.3%

  Self-reported

• ARC-AGI v2

  #12 / 19

  ARC-AGI-2 is an upgraded benchmark for measuring abstract reasoning and problem-solving abilities in AI systems through visual grid transformation tasks. It evaluates fluid intelligence via input-output grid pairs (1x1 to 30x30) using colored cells (0-9), requiring models to identify underlying transformation rules from demonstration examples and apply them to test cases. Designed to be easy for humans but challenging for AI, focusing on core cognitive abilities like spatial reasoning, pattern recognition, and compositional generalization.

  37.6%

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

• GPQA (diamond)

  #7 / 10

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

  81.3%

  Unverified

• MMMU (validation)

  #1 / 4

  Validation set of the Massive Multi-discipline Multimodal Understanding and Reasoning benchmark. Features college-level multimodal questions across 6 core disciplines (Art & Design, Business, Science, Health & Medicine, Humanities & Social Science, Tech & Engineering) spanning 30 subjects and 183 subfields with diverse image types including charts, diagrams, maps, and tables.

  80.7%

  Self-reported