Compare Start here

AnthropicLanguage model

Claude Opus 4.7

Anthropic language model.

Compare head-to-head Race it in 3D

Overall Intelligence

#15

of 61
23.6 pts behind #1

1

races led

84

weeks at #1

67.5

score

Released: Apr 16, 2026; 6 mo ago
Context: 1M; 128K max output
Price: $5 / $25; per 1M in/out · $10.00 blended · OpenRouter
Speed: —; not measured
Modalities: text · image; outputs text
Weights: Closed; API and apps

The 30-second version

Anthropic language model.

Key takeaways

1Anthropic language model.

Where it ranks

Latest real results · click any race to watch it

Opus 4.7Best on each axis

Overall

15Overall+23.6 pts

Coding

31Frontend & UI+249 Elo 8Coding Q&A+28 Elo 31React Web Apps+295 Elo 1Debugging & Repair83.5

Hard Reasoning

20Hard Reasoning+36.0 pts 33Frontier Questions+19.1 pts 15ARC-AGI-2+19.2 pts 15Common-Sense Reasoning+20.2 pts

Math

19Math+28.9 pts 23Competition Math+2.2 pts 21Research Math+23.5 pts 15Math Chat+38 Elo

Science

15Science+25.3 pts 32Graduate Science QA+6.3 pts 9Medicine & Health+59 Elo 10Science Q&A+40 Elo

Writing & Language

9Writing & Language+9.6 pts 10Creative Writing+48 Elo 8Professional Writing+42 Elo 11Multilingual+41 Elo 7Instruction Following+38 Elo 4Conversation+50 Elo

Multimodal

6Multimodal+9.3 pts 5Image Understanding+8 Elo 5Documents & Charts+21 Elo

Tool Use & Agents

11Tool Use & Agents+41.0 pts 22Tool Use+16.7 pts 4Computer Use+13.2 pts 9Web Search+31 Elo

Long Context

43Long Context+60.9 pts 43Long-Document Reasoning+10.0 pts

Speed & Cost

51Intelligence per Dollar+614.0 pts

Trust & Factuality

21Trust & Factuality+40.1 pts 23Factuality+24.3 pts 7Calibration+27.0 pts

Overall Intelligence over time

#1 frontierOpus 4.7MiMo-V2.6-ProQwen3.8-Max

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 4.7April 2026 Opus 4.8May 2026 Opus 5July 2026 Opus 5.5September 2026

60-second briefing

Opus 4.7, explained

Animated summary · captions from the auto-written script

Currently leads

Debugging & Repair

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 4.7 is 15th in overall intelligence; leader is Claude Opus 5.5.