Claude Opus 5
Anthropic · 5 thinking configurations
Intelligence44.8
Input / 1M$5.00
Output / 1M$25.00
Context1M
Tariff: Anthropic · Source: artificial-analysis · USD per million tokens
Thinking configuration
What does more thinking buy you?
Compare this model’s measured thinking configurations.
Scroll the chart ↔ · tap a point for details
Efficient frontier: best measured score at each cost5 measured configurations · 0 without both values
Selected: thinking medium · Click a point to switch configuration
Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis...
Intelligence IndexArtificial Analysis composite index, not a percentage. Different versions of the index are not directly comparable.
44.8 pointsDeepSWE · pass@1Software-engineering tasks on mini-swe-agent v1.1. Pass@1 across evaluated runs, with measured cost per task. The 95% intervals may overlap.
68.9 % ±1.2GPQA DiamondGraduate-level scientific questions. Measures specialist reasoning rather than web-search quality.
91.9 %Humanity’s Last ExamDifficult questions across many disciplines, compared under the same evaluation setup.
51.3 %SciCodeCode generation for scientific research problems.
51.5 %Terminal-Bench 2.1Agent tasks in a terminal environment. Results also depend on the evaluation harness.
86.1 %MMMU-ProMultimodal understanding of academic problems that include images.
81.6 %Omniscience accuracyFactual accuracy in Artificial Analysis's Omniscience evaluation.
57.1 %Specifications from the catalog
Inputtext, image, file
Outputtext
Tool callingYes
Structured outputYes
Speed52.5 tok/s
First token10.93 s
Maximum output128K
Catalog listing date2026-07-24
DeepSWE v1.1 · 113 tasks · mini-swe-agent · cost $3.29 / task · 52 mean steps · 37K mean output tokens. Published by the source 9/22/2026.