Claude 3.5 Sonnet
Claude 3.5 Sonnet raises the industry bar for intelligence, outperforming competitor models and Claude 3 Opus on a wide range of evaluations, with the speed and cost of a mid-tier model. It operates at twice the speed of Claude 3 Opus.
Specifications
- Architecture
- Decoder-only Transformer
- License
- Proprietary
- Context Window
- 200,000 tokens
- Max Output
- 8,192 tokens
- Training Data Cutoff
- Apr 2024
- Type
- multimodal
- Modalities
- textimage
Benchmark Scores
Graduate-level Problems in Quantitative Analysis (GPQA) evaluates advanced reasoning on graduate-lev...
Massive Multitask Language Understanding (MMLU) tests knowledge across 57 subjects including mathema...
Evaluates code generation capabilities by asking models to complete Python functions based on docstr...
Multilingual Grade School Math (MGSM) extends GSM8K to 10 languages....
Discrete Reasoning Over Paragraphs (DROP) requires models to resolve references in a passage and per...
Beyond the Imitation Game Benchmark (BIG-bench) is a collaborative benchmark of 204 diverse tasks....
A dataset of 12,500 challenging competition mathematics problems requiring multi-step reasoning....
Grade School Math 8K (GSM8K) consists of 8.5K high-quality grade school math word problems....
Advanced Specifications
- Model Family
- Claude
- API Access
- Available
- Chat Interface
- Available
- Multilingual Support
- Yes
Capabilities & Limitations
- Capabilities
- advanced reasoningcode generationmathematicsmultilingual problem-solvingtext comprehensionknowledge retrieval
- Function Calling Support
- Yes
- Tool Use Support
- Yes
