Anthropic's most intelligent model in the 3.5 family, featuring Artifacts for creating and editing applications in real-time.
| Benchmark | Description | Score | Category | Bar |
|---|---|---|---|---|
| MMLU | Massive Multitask Language Understanding | 88.3% | knowledge | |
| HumanEval | Code generation accuracy | 92% | coding | |
| MATH | Mathematical reasoning | 88.3% | math | |
| GSM8K | Grade school math | 90% | math | |
| GPQA | Graduate-level science Q&A | 59.4% | reasoning | |
| HellaSwag | Common sense reasoning | 88.7% | reasoning | |
| SWE-bench | Software engineering problems | 43.3% | coding | |
| ARC-C | AI2 Reasoning Challenge | 96% | reasoning |