Compare Start here

AnthropicLanguage modelSuperseded

Claude Opus 4.1

Incremental Opus upgrade focused on real-world coding precision.

Compare head-to-head Race it in 3D

Overall Intelligence

#40

of 56
19.0 pts behind #1

0

races led

30

weeks at #1

69.7

score

Released: Aug 5, 2025; 1.2 yr ago
Context: 200K; 32K max output
Price: $15 / $75; per 1M in/out · $30.00 blended
Speed: 40 tok/s; 4s to first token
Modalities: text · image; outputs text
Weights: Closed; API and apps

The 30-second version

Incremental Opus upgrade focused on real-world coding precision.

Key takeaways

1Incremental Opus upgrade focused on real-world coding precision.

Where it ranks

Current snapshot · illustrative scores · click any race to watch it

Opus 4.1Best on each axis

Overall

40Overall+19.0 pts

Coding

36Coding+18.1 pts 35Frontend & UI+96 Elo 36Backend & APIs+15.8 pts 41Distributed Systems+21.3 pts 37Full-Stack Apps+18.2 pts 37Debugging & Repair+18.4 pts 36Agentic Coding+18.5 pts 37Code Review & Security+16.8 pts 38Data Science & SQL+15.7 pts 36Mobile Apps+15.0 pts 36Terminal & DevOps+20.0 pts 43Competitive Programming+628

Hard Reasoning

42Hard Reasoning+20.6 pts 42Frontier Questions+35.9 pts 39Abstract & Novel Reasoning+30.0 pts 42Logic & Puzzles+19.3 pts 37Planning & Strategy+17.3 pts

Math

44Math+22.7 pts 45Competition Math+17.6 pts 44Research Math+29.6 pts 43Applied & Quantitative+18.5 pts

Science

42Science+19.3 pts 41Graduate Science QA+11.6 pts 40Biology & Medicine+16.2 pts 42Physics & Chemistry+17.6 pts 41Research Assistance+17.9 pts

Writing & Language

39Writing & Language+17.8 pts 37Creative Writing+106 Elo 35Technical Writing+13.4 pts 38Editing & Style+13.8 pts 41Multilingual+12.4 pts 41Instruction Following+13.7 pts 40Conversation & EQ+110 Elo

Multimodal

38Multimodal+33.1 pts 36Image Understanding+19.1 pts 35Documents & Charts+17.8 pts 39Video Understanding+35.1 pts 40Speech & Audio+44.6 pts

Tool Use & Agents

37Tool Use & Agents+19.2 pts 38Tool Use+14.7 pts 33Computer Use+25.8 pts 42Web Research+25.6 pts 37Long-Horizon+25.6 hrs

Long Context

42Long Context+24.2 pts 431M Recall+20.6 pts 41Long Reasoning+20.8 pts

Speed & Cost

56Speed & Cost+62.8 pts 54Output Speed+483 tok/s 26Latency+3.50s 55Cost-Efficiency+83.3 pts

Trust & Factuality

37Trust & Factuality+17.5 pts 35Factuality+13.9 pts 37Honesty & Calibration+15.0 pts

Overall Intelligence over time

#1 frontierOpus 4.1V4.1 FlashGLM-5.3

Update history

The distilled version first; open any release for the deeper breakdown.

The Claude Opus family

Opus 4May 2025 Opus 4.1August 2025 Opus 4.5November 2025 Opus 4.6February 2026 Opus 4.8May 2026 Opus 5July 2026 Opus 5.5September 2026

60-second briefing

Opus 4.1, explained

AI video summary · placeholder render from the auto-written script

From Anthropic's own guide, distilled

Prompt engineering and Claude best practices

Be explicit about the outcome you want; newer Claude models follow instructions literally rather than guessing at hidden intent.
Explain why a rule exists. Context about the goal lets the model generalise the rule to cases you did not list.
Wrap documents, examples and data in XML-style tags so instructions and material never blur together.
Put long documents at the top of the prompt and your question at the end; recall and grounding both improve.
For agentic tasks, state when to act versus when to ask, and ask for a short plan before large edits.

All official guides, distilled →

About Anthropic

Safety-focused lab building the Claude family of models.

Optimising for

Reliable long-horizon agentic work (especially coding and computer use), honest and calibrated answers, and strong writing, with safety research shipped alongside capability.

San Francisco, US · founded 2021

Closest rivals

Opus 4.1 is 40th in overall intelligence; leader is Claude Opus 5.5.