Claude 3.5 Sonnet v2
Anthropic·
LLMsmidcloud
Overview
Upgraded Sonnet with computer use capabilities.
Capabilities and innovations
Computer useEnhanced codingTool useComputer UseAgent CapabilitiesReal-world Interaction
Benchmarks
| Benchmark | Score | Source |
|---|---|---|
| GPQA Diamond | 65% | unsourced |
| Humanity’s Last Exam (no tools) | 11.5% | unsourced |
| SWE-bench Verified | 49% | unsourced |
| MMLU | 88.3% | unsourced |
- SWE-bench Pro: benchmark did not exist at release
- MMLU-Pro: benchmark did not exist at release
- Terminal-Bench 2.x: benchmark did not exist at release
- MMMU-Pro: benchmark did not exist at release
Links
More from Anthropic
Data curated by AI Model Timeline. See the methodology for admission criteria, benchmark eras and source priority.