CL

Claude Sonnet 4

Reasoning modelSonnetClaude 4

Claude Sonnet 4

Release date: 2025-05-23Updated: 2025-10-19 12:24:142,104
Live demoGitHubHugging FaceCompare
Parameters
Not disclosed
Context length
200K
Chinese support
Supported
Reasoning ability

Claude Sonnet 4 is an AI model published by Anthropic, released on 2025-05-23, for Reasoning model, and 200K context length, under the 不开源 license, with a 1223.00 score on CodeClash.

Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology

Claude Sonnet 4

Model basics

Reasoning traces
Supported
Thinking modes
Thinking modes not supported
Context length
200K tokens
Max output length
64K tokens
Model type
Reasoning model
Modality (in / out)
Text, Image → Text
Release date
2025-05-23
Model file size
No data
MoE architecture
No
Total params / Active params
No data / N/A
Knowledge cutoff
No data
Claude Sonnet 4

Open source & experience

Code license
不开源
Weights license
不开源
GitHub repo
GitHub link unavailable
Hugging Face
Hugging Face link unavailable
Live demo
No live demo
Claude Sonnet 4

Official resources

Claude Sonnet 4

API details

API speed
4/5
No public API pricing yet.
Claude Sonnet 4

Benchmark Results

Claude Sonnet 4 currently shows benchmark results led by SWE-bench Verified (13 / 108, score 80.20), Terminal-Bench (10 / 35, score 41.30), MMLU Pro (37 / 126, score 84). This page also consolidates core specs, context limits, and API pricing so you can evaluate the model from benchmark results and deployment constraints together.

Thinking
Tool usage

General Knowledge

12 evaluations
Benchmark / mode
Score
Rank/total
84
37 / 126
83.80
58 / 179
75.40
92 / 179
68
123 / 179
LiveBench
Standard Mode
50.98
89 / 115
61.27
65 / 115
40
46 / 65
23.80
53 / 65
9.60
136 / 159
5.52
150 / 159
5.90
43 / 59
1.30
52 / 59

Coding and Software Engineer

6 evaluations
Benchmark / mode
Score
Rank/total
CodeClash
Standard ModeTools
1223
4 / 8
80.20
13 / 108
72.70
47 / 108
66
58 / 120
48.50
94 / 120

Math and Reasoning

12 evaluations
Benchmark / mode
Score
Rank/total
85
50 / 106
70.50
71 / 106
38
95 / 106
43.40
50 / 62
27.10
8 / 16
9.70
5 / 10
5.20
8 / 10
4.10
41 / 60
4
5 / 9
3.30
6 / 9
0
72 / 80

Writing and Creative Capabilities

1 evaluations
Benchmark / mode
Score
Rank/total
83.05
14 / 23

AI Agent - Tool Usage

4 evaluations
Benchmark / mode
Score
Rank/total
42.20
16 / 18
41.30
10 / 35
35.50
18 / 35

Multimodal Understanding

1 evaluations
Benchmark / mode
Score
Rank/total
76.50
16 / 28

常识推理

1 evaluations
Benchmark / mode
Score
Rank/total
Simple Bench
Thinking Mode
45.50
34 / 63

Agent Level Benchmark

4 evaluations
Benchmark / mode
Score
Rank/total
Aider-Polyglot
Standard Mode
56.40
26 / 59
61.30
20 / 59
52
33 / 40

Instruction Following

1 evaluations
Benchmark / mode
Score
Rank/total
55
22 / 29

Productivity Knowledge

1 evaluations
Benchmark / mode
Score
Rank/total
33
19 / 21

Long Context

1 evaluations
Benchmark / mode
Score
Rank/total
65
10 / 13

Claw-style Agent Evaluation

2 evaluations
Benchmark / mode
Score
Rank/total
Pinch Bench
Thinking ModeTools
80.50
22 / 37
Claw Bench
Thinking ModeTools
77.80
23 / 29

Compare with other models

No curated comparisons for this model yet.

Want a custom combination? Open the compare tool

Claude Sonnet 4

Publisher

Claude Sonnet 4

Model Overview

Claude Sonnet 4 is an AI model published by Anthropic, released on 2025-05-23, for Reasoning model, and 200K context length, under the 不开源 license, with a 1223.00 score on CodeClash.

DataLearner on WeChat

Follow DataLearner on WeChat for AI model updates and research notes.

DataLearner WeChat QR code