Skip to main content

Claude 4 Sonnet

AnthropicEstablishedReleased May 2025
Overall Score
Est. 50Prov. #67 of 119
Arena Elo
1239
Categories Ranked
8of 8
Price (1M tokens)
$3 in / $15 out
Speed
40tok/s
Context
200K
ProprietaryNon-Reasoning
Confidence
base

According to BenchLM.ai, Claude 4 Sonnet ranks #67 out of 119 models on the provisional leaderboard with an overall score of 50/100. It does not yet have enough sourced coverage for BenchLM's verified leaderboard. While not a frontier model, it offers specific advantages depending on the use case.

Claude 4 Sonnet is a proprietary model with a 200K token context window. It processes queries without explicit chain-of-thought reasoning, offering faster response times and lower token usage.

This profile currently has 19 of 225 tracked benchmarks. BenchLM only exposes non-generated benchmark rows publicly, so missing categories stay blank until a sourced evaluation is available.

Its strongest category is Multimodal & Grounded (#21), while its weakest is Instruction Following (#70). This performance profile makes it particularly strong for screenshots, documents, charts, and grounded multimodal workflows.

Ranking Distribution

Category rank across 8 benchmark categories — sorted by best rank

Category Performance

Scores across all benchmark categories (0-100 scale)

Category Breakdown

Agentic

#53
44.6/ 100
Weight: 22%5 benchmarks
Terminal-Bench 2.0BrowseCompOSWorld-VerifiedGAIATAU-benchWebArena

Coding

#51
53.9/ 100
Weight: 20%4 benchmarks
SWE-bench VerifiedLiveCodeBenchSWE-bench ProSWE-RebenchSciCode

Reasoning

#48
54.3/ 100
Weight: 17%2 benchmarks
MuSRLongBench v2MRCRv2ARC-AGI-2

Knowledge

#58
50.1/ 100
Weight: 12%6 benchmarks
GPQASuperGPQAMMLU-ProHLEFrontierScienceSimpleQA

Math

#41
61.1/ 100
Weight: 5%0 benchmarks
AIME 2025BRUMO 2025MATH-500FrontierMath

Multilingual

#36
69.2/ 100
Weight: 7%0 benchmarks
MGSMMMLU-ProX

Multimodal

#21
74.7/ 100
Weight: 12%1 benchmark
MMMU-ProOfficeQA ProCharXivCharXiv w/o tools

Inst. Following

#70
58.6/ 100
Weight: 5%1 benchmark
IFEvalIFBench

Chatbot Arena Performance

Text Overall1239

Benchmark Details

Only benchmark rows with an attached exact-source record are shown here. Source-unverified manual rows and generated rows are hidden from model pages.

Frequently Asked Questions

How does Claude 4 Sonnet perform overall in AI benchmarks?

Claude 4 Sonnet currently ranks #67 out of 119 models on BenchLM's provisional leaderboard with an overall score of 50 (estimated). It is created by Anthropic and features a 200K context window.

Is Claude 4 Sonnet good for knowledge and understanding?

Claude 4 Sonnet ranks #58 out of 119 models in knowledge and understanding benchmarks with an average score of 50.1. There are stronger options in this category.

Is Claude 4 Sonnet good for coding and programming?

Claude 4 Sonnet ranks #51 out of 119 models in coding and programming benchmarks with an average score of 53.9. There are stronger options in this category.

Is Claude 4 Sonnet good for reasoning and logic?

Claude 4 Sonnet ranks #48 out of 119 models in reasoning and logic benchmarks with an average score of 54.3. There are stronger options in this category.

Is Claude 4 Sonnet good for agentic tool use and computer tasks?

Claude 4 Sonnet ranks #53 out of 119 models in agentic tool use and computer tasks benchmarks with an average score of 44.6. There are stronger options in this category.

Is Claude 4 Sonnet good for multimodal and grounded tasks?

Claude 4 Sonnet ranks #21 out of 119 models in multimodal and grounded tasks benchmarks with an average score of 74.7. There are stronger options in this category.

Is Claude 4 Sonnet good for instruction following?

Claude 4 Sonnet ranks #70 out of 119 models in instruction following benchmarks with an average score of 58.6. There are stronger options in this category.

Does Claude 4 Sonnet have full benchmark coverage on BenchLM?

Not yet. Claude 4 Sonnet currently has 19 published benchmark scores out of the 225 benchmarks BenchLM tracks. BenchLM only exposes non-generated public benchmark rows, so missing categories stay blank until a sourced evaluation is available.

What is the context window size of Claude 4 Sonnet?

Claude 4 Sonnet has a context window of 200K, which determines how much text it can process in a single interaction.

Last updated: June 2, 2026 · Runtime metrics stay blank until BenchLM has a sourced snapshot.

Don't miss the next GPT moment

Which models moved up, what’s new, and what it costs. One email a week, 3-min read.

Free. One email per week.