Claude3-Opus
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
Model basics
Open source & experience
Official resources
API details
| Type | Condition | Input | Output |
|---|---|---|---|
| Text | - | $15.00/ 1M tokens | $75.00/ 1M tokens |
| Image | - | $15.00/ 1M tokens | — |
| Type | Condition | Input | Output |
|---|---|---|---|
| Text | - | $7.50/ 1M tokens | $37.50/ 1M tokens |
| Image | - | $7.50/ 1M tokens | — |
| Type | TTL | Write | Read |
|---|---|---|---|
| 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.
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.
General Knowledge
2 evaluationsCommon Sense Reasoning
2 evaluationsPublisher
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.
