Compare Start here

AnthropicLanguage model

Claude Sonnet 5

Anthropic language model.

Compare head-to-head Race it in 3D

Overall Intelligence

#38

of 61
46.7 pts behind #1

0

races led

0

weeks at #1

44.4

score

Released: Jun 30, 2026; 4 mo ago
Context: 1M; 128K max output
Price: $2 / $10; per 1M in/out · $4.00 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

Sonnet 5Best on each axis

Overall

38Overall+46.7 pts

Coding

25Coding+50.7 pts 36Frontend & UI+267 Elo 36Coding Q&A+63 Elo 35React Web Apps+314 Elo 11Agentic Coding+16.3 pts 30Terminal & DevOps+49.5 pts

Hard Reasoning

28Hard Reasoning+45.4 pts 34Frontier Questions+20.1 pts 18Common-Sense Reasoning+21.3 pts

Math

36Math+50.1 pts 33Competition Math+5.3 pts 29Research Math+28.1 pts 33Math Chat+69 Elo

Science

41Science+55.5 pts 30Graduate Science QA+5.9 pts 43Medicine & Health+111 Elo 31Scientific Coding+12.6 pts 36Science Q&A+88 Elo

Writing & Language

41Writing & Language+56.4 pts 42Creative Writing+117 Elo 40Professional Writing+99 Elo 42Multilingual+91 Elo 36Instruction Following+83 Elo 37Conversation+103 Elo

Multimodal

25Multimodal+50.9 pts 29Image Understanding+52 Elo 14Documents & Charts+50 Elo

Tool Use & Agents

18Tool Use & Agents+56.7 pts 19Tool Use+14.0 pts 21Web Search+70 Elo

Long Context

24Long Context+31.2 pts 24Long-Document Reasoning+6.7 pts

Speed & Cost

38Intelligence per Dollar+609.3 pts

Trust & Factuality

50Trust & Factuality+91.5 pts 44Factuality+42.3 pts

Overall Intelligence over time

#1 frontierSonnet 5Grok 4.7GLM-5.2

Update history

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

The Claude Sonnet family

3.7 SonnetFebruary 2025 Sonnet 4.5September 2025 Sonnet 4.6February 2026 Sonnet 5June 2026 Sonnet 5.5September 2026

60-second briefing

Sonnet 5, explained

Animated summary · captions 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

Sonnet 5 is 38th in overall intelligence; leader is Claude Opus 5.5.