DataLearner logoDataLearnerAI
Latest AI Insights
Model Leaderboards
Benchmarks
Model Directory
Model Comparison
Resource Center
Tools
LanguageEnglish
DataLearner logoDataLearner AI

A knowledge platform focused on LLM benchmarking, datasets, and practical instruction with continuously updated capability maps.

Products

  • Leaderboards
  • Model comparison
  • Datasets

Resources

  • Tutorials
  • Editorial
  • Tool directory

Company

  • About
  • Privacy policy
  • Data methodology
  • Contact

© 2026 DataLearner AI. DataLearner curates industry data and case studies so researchers, enterprises, and developers can rely on trustworthy intelligence.

Privacy policyTerms of service
Page navigation
Page navigation
Model catalogClaude Opus 4.6
CL

Claude Opus 4.6

Reasoning model

Anthropic Claude Opus 4.6

Release date: 2026-02-05Updated: 2026-04-17 10:24:37.668Knowledge cutoff: 2025-053,717
Live demoGitHubHugging FaceCompare
Parameters
Not disclosed
Context length
1000K
Chinese support
Supported
Reasoning ability

Anthropic Claude Opus 4.6 is an AI model published by Anthropic, released on 2026-02-05, for Reasoning model, and 1000K tokens context length, requiring about 0B storage, with no open-source license.

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

Claude Opus 4.6

Model basics

Reasoning traces
Supported
Thinking modes
Thinking Level · Extended (Default)Standard ModeThinking Level · LowThinking Level · MediumThinking Level · High
Context length
1000K tokens
Max output length
65536 tokens
Model type
Reasoning model
Release date
2026-02-05
Model file size
0B
MoE architecture
No
Total params / Active params
No data / N/A
Knowledge cutoff
2025-05
Claude Opus 4.6

Open source & experience

Code license
Not open source
Weights license
Not open source
GitHub repo
GitHub link unavailable
Hugging Face
Hugging Face link unavailable
Live demo
https://claude.ai/new
Claude Opus 4.6

Official resources

Paper
Introducing Claude Opus 4.6
DataLearnerAI blog
No blog post yet
Claude Opus 4.6

API details

API speed
3/5
💡Default unit: $/1M tokens. If vendors use other units, follow their published pricing.
Learn about pricing modes
Standard
TypeConditionInputOutput
TextContext > 200K$10.00/ 1M$37.50/ 1M
TextContext <= 200K$5.00/ 1M$25.00/ 1M
Batch
TypeConditionInputOutput
Text-$2.50/ 1M$12.50/ 1M
Turbo
TypeConditionInputOutput
TextContext <= 200K$30.00/ 1M$150.00/ 1M
TextContext > 200K$60.00/ 1M$225.00/ 1M
Cache PricingPrompt Cache
TypeTTLWriteRead
Text5m$6.25/ 1M
Context <= 200K
$0.500/ 1M
Context <= 200K
Text5m$12.50/ 1M
Context > 200K
$1.00/ 1M
Context > 200K
Text10m$10.00/ 1M
Context <= 200K
$0.500/ 1M
Context <= 200K
Text10m$20.00/ 1M
Context > 200K
$1.00/ 1M
Context > 200K
Claude Opus 4.6

Benchmark Results

Claude Opus 4.6 currently shows benchmark results led by τ²-Bench (1 / 40, score 91.89), IF Bench (1 / 27, score 94), GDPval-AA (1 / 20, score 1606). 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
Internet

General Knowledge

8 evaluations
Benchmark / mode
Score
Rank/total
ARC-AGI
Low
86
20 / 65
ARC-AGI
Extended
92
11 / 65
GPQA Diamond
Extended
91.31
12 / 175
MMLU
Extended
91.05
7 / 65
ARC-AGI-2
Low
64.60
15 / 58
ARC-AGI-2
Extended
66.30
14 / 58
HLE
ExtendedToolsInternet
53
8 / 149
ARC-AGI-3
Max
0
1 / 6

Coding and Software Engineer

5 evaluations
Benchmark / mode
Score
Rank/total
HumanEval
Extended
95
2 / 39
SWE-bench Verified
ExtendedTools
80.84
6 / 103
SWE-bench
ExtendedTools
77.83
1 / 2
LiveCodeBench
Extended
76
35 / 118
SWE-bench Multilingual
ExtendedTools
72
9 / 17

Common Sense

1 evaluations
Benchmark / mode
Score
Rank/total
SimpleQA
Extended
72
6 / 45

Math and Reasoning

7 evaluations
Benchmark / mode
Score
Rank/total
AIME2025
Extended
99.79
7 / 106
MATH-500
Extended
97.60
10 / 44
FrontierMath
Max
40.70
7 / 60
FrontierMath - Tier 4
64K
20.80
14 / 80
FrontierMath - Tier 4
32K
20.80
14 / 80
FrontierMath - Tier 4
High
14.60
23 / 80
FrontierMath - Tier 4
Max
22.90
12 / 80

Multimodal Understanding

2 evaluations
Benchmark / mode
Score
Rank/total
MMMU
Extended
73.90
18 / 28
MMMU
ExtendedTools
77.30
15 / 28

Agent Level Benchmark

2 evaluations
Benchmark / mode
Score
Rank/total
τ²-Bench - Telecom
ExtendedTools
99.25
2 / 35
τ²-Bench
ExtendedTools
91.89
1 / 40

Instruction Following

1 evaluations
Benchmark / mode
Score
Rank/total
IF Bench
Extended
94
1 / 27

AI Agent - Information Search

1 evaluations
Benchmark / mode
Score
Rank/total
BrowseComp
Thinking ModeToolsInternet
84
6 / 43

AI Agent - Tool Usage

2 evaluations
Benchmark / mode
Score
Rank/total
OSWorld-Verified
ExtendedTools
72.70
6 / 14
Terminal Bench 2.0
ExtendedTools
65.40
9 / 43

Productivity Knowledge

1 evaluations
Benchmark / mode
Score
Rank/total
GDPval-AA
ExtendedToolsInternet
1606
1 / 20

Claw-style Agent Evaluation

1 evaluations
Benchmark / mode
Score
Rank/total
Pinch Bench
Thinking ModeTools
87.40
7 / 37
View benchmark analysisCompare with other models

Compare with other models

  • Peer modelClaude Opus 4.6 vs Gemini 3.1 Pro Preview15 benchmarks
  • Earlier versionClaude Opus 4.6 vs Opus 4.514 benchmarks
  • Peer modelClaude Opus 4.6 vs GPT-5.412 benchmarks
  • Earlier versionClaude Opus 4.6 vs Claude Opus 411 benchmarks
  • Earlier versionClaude Opus 4.6 vs Opus 4.16 benchmarks

Want a custom combination? Open the compare tool

Claude Opus 4.6

Publisher

Anthropic
Anthropic
View publisher details
Anthropic Claude Opus 4.6

Model Overview

Anthropic Claude Opus 4.6 is an AI model published by Anthropic, released on 2026-02-05, for Reasoning model, and 1000K tokens context length, requiring about 0B storage, with no open-source license.

DataLearner on WeChat

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

DataLearner WeChat QR code