DataLearner logo
CL

Claude3-Opus

Retired · 2026-01-05Multimodal modelOpusClaude 3

Claude3-Opus

Release date: 2024-03-04Updated: 2026-09-04Retired: 2026-01-05Views: 1,024
Live demoGitHubHugging FaceCompare
Parameters
No data
Context length
200K
Multilingual
Supported
Reasoning ability
No data

Claude3-Opus is an AI model published by Anthropic, released on 2024-03-04, for Multimodal model, and 200K context length, with a 95.40 score on HellaSwag.

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

Claude3-Opus

Model basics

Reasoning traces
No data
Thinking modes
Thinking modes not supported
Context length
200K tokens
Max output length
No data
Model type
Multimodal model
Modality (in / out)
No data
Release date
2024-03-04
Model file size
No data
MoE architecture
No
Total params / Active params
No data / Not applicable
Knowledge cutoff
No data
Claude3-Opus

Open source & experience

Code license
Proprietary
Weights license
Proprietary
GitHub repo
N/A
Hugging Face
N/A
Live demo
N/A
Claude3-Opus

Official resources

Paper
DataLearnerAI blog
Claude3-Opus

API details

API speed
No data
💡Default unit: $/1M tokens. If vendors use other units, follow their published pricing.
Standard
TypeConditionInputOutput
Text-$15.00/ 1M tokens$75.00/ 1M tokens
Image-$15.00/ 1M tokens
Batch
TypeConditionInputOutput
Text-$7.50/ 1M tokens$37.50/ 1M tokens
Image-$7.50/ 1M tokens
Cache PricingPrompt Cache
TypeTTLWriteRead
Text-$18.75/ 1M tokens$1.50/ 1M tokens
Text-$18.75/ 1M tokens
Cache = write
Text-$1.50/ 1M tokens
Cache = hit
Image-$18.75/ 1M tokens
Cache = write
Image-$1.50/ 1M tokens
Cache = hit

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

Claude3-Opus

Benchmark Results

Claude3-Opus currently shows benchmark results led by GSM8K (8 / 70, score 95), MMLU (28 / 124, score 86.80), HumanEval (37 / 140, score 84.90). 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

General Knowledge

2 evaluations
Benchmark / mode
Score
Rank/total
MMLU
Standard Mode
86.80
28 / 124
MMLU Pro
Standard Mode
68.45
101 / 134

Math and Reasoning

2 evaluations
Benchmark / mode
Score
Rank/total
GSM8K
Standard Mode
95
8 / 70
MATH
Standard Mode
60.10
31 / 42

Coding and Software Engineer

1 evaluations
Benchmark / mode
Score
Rank/total
HumanEval
Standard Mode
84.90
37 / 140

Common Sense Reasoning

2 evaluations
Benchmark / mode
Score
Rank/total
HellaSwag
Standard Mode
95.40
1 / 3
SimpleBench
Standard Mode
23.50
83 / 94

Reading Comprehension

1 evaluations
Benchmark / mode
Score
Rank/total
DROP
Standard Mode
83.10
6 / 9

General Evaluation

1 evaluations
Benchmark / mode
Score
Rank/total
GPQA Diamond
Standard Mode
50.40
245 / 274
Claude3-Opus

Publisher

Claude3-Opus

Model Overview

Claude3-Opus is an AI model published by Anthropic, released on 2024-03-04, for Multimodal model, and 200K context length, with a 95.40 score on HellaSwag.

DataLearner on WeChat

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

DataLearner WeChat QR code