DataLearner logo
OP

Opus 4.1

Reasoning modelOpusClaude 4.1

Claude Opus 4.1

Release date: 2025-08-06Updated: 2026-06-15Knowledge cutoff: 2025-01Views: 1,002
Live demoGitHubHugging FaceCompare
Parameters
No data
Context length
200K
Multilingual
Supported
Reasoning ability
4/5

Claude Opus 4.1 is an AI model published by Anthropic, released on 2025-08-06, for Reasoning model, and 200K context length, with a 88.00 score on MMLU Pro.

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

Opus 4.1

Model basics

Reasoning traces
Supported
Thinking modes
Thinking Level · Extended (Default)Standard Mode
Context length
200K tokens
Max output length
32K tokens
Model type
Reasoning model
Modality (in / out)
Text, Image → Text
Release date
2025-08-06
Model file size
No data
MoE architecture
No
Total params / Active params
No data / Not applicable
Knowledge cutoff
2025-01
Opus 4.1

Open source & experience

Code license
Proprietary
Weights license
Proprietary
GitHub repo
N/A
Hugging Face
N/A
Live demo
Opus 4.1

Official resources

Paper
DataLearnerAI blog
N/A
Opus 4.1

API details

API speed
2/5
💡Default unit: $/1M tokens. If vendors use other units, follow their published pricing.
Standard
TypeConditionInputOutput
Text-$15.00/ 1M$75.00/ 1M
Image-$15.00/ 1M
Batch
TypeConditionInputOutput
Text-$7.50/ 1M$37.50/ 1M
Image-$7.50/ 1M
Cache PricingPrompt Cache
TypeTTLWriteRead
Text-$18.75/ 1M
Cache = write
Text-$1.50/ 1M
Cache = hit
Text5m$18.75/ 1M$1.50/ 1M
Image-$18.75/ 1M
Cache = write
Image-$1.50/ 1M
Cache = hit

“—” means the modality is not billed in that direction, or the vendor has not published a price for it.

Opus 4.1

Benchmark Results

Opus 4.1 currently shows benchmark results led by MMLU Pro (7 / 133, score 88), Terminal-Bench (5 / 35, score 46.50), SimpleBench (19 / 67, score 60). 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

3 evaluations
Benchmark / mode
Score
Rank/total
MMLU Pro
Extended
88
7 / 133
LiveBench
Standard Mode
54.45
82 / 115
61.81
60 / 115

General Evaluation

1 evaluations
Benchmark / mode
Score
Rank/total
GPQA Diamond
Extended
81
135 / 270

Coding and Software Engineer

1 evaluations
Benchmark / mode
Score
Rank/total
SWE-bench Verified
ExtendedTools
74.50
41 / 114

Math and Reasoning

9 evaluations
Benchmark / mode
Score
Rank/total
AIME2025
Extended
78
60 / 106
IMO 2024
Standard Mode
18.70
3 / 10
12.63
56 / 58
IMO 2025
Standard Mode
11.70
4 / 9
FrontierMath
Standard Mode
5.90
35 / 60
FrontierMath
Extended
7.20
33 / 60
4.20
40 / 80
4.20
40 / 80

AI Agent - Tool Usage

2 evaluations
Benchmark / mode
Score
Rank/total
46.50
5 / 35
Terminal-Bench
ExtendedTools
43.30
9 / 35

Common Sense Reasoning

1 evaluations
Benchmark / mode
Score
Rank/total
SimpleBench
Extended
60
19 / 67

Instruction Following

1 evaluations
Benchmark / mode
Score
Rank/total
IF Bench
ExtendedTools
55
27 / 34

Agent Level Benchmark

1 evaluations
Benchmark / mode
Score
Rank/total
Terminal Bench Hard
ExtendedTools
32
9 / 13
Opus 4.1

Publisher

Claude Opus 4.1

Model Overview

Claude Opus 4.1 is an AI model published by Anthropic, released on 2025-08-06, for Reasoning model, and 200K context length, with a 88.00 score on MMLU Pro.

DataLearner on WeChat

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

DataLearner WeChat QR code