Compare / Claude Sonnet 4.5 vs Nemotron 3 Super
Claude Sonnet 4.5 vs Nemotron 3 Super
13 results from 2 sources that measured both models. Each row is in the source's own units; there is no overall winner.
| Benchmark | Metric | Claude Sonnet 4.5 | Nemotron 3 Super |
|---|---|---|---|
| Arena (formerly LMArena)reported | OverallArena rating | 1,449 | 1,390 |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,461 | 1,350 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,454 | 1,303 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,498 | 1,393 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,464 | 1,343 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,457 | 1,360 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,454 | 1,325 |
| OpenHands Indexreported | Average% resolved | 53.0% | 36.2% |
| OpenHands Indexreported | Front end (SWE-Bench Multimodal)% resolved | 36.8% | 20.6% |
| OpenHands Indexreported | Greenfield (Commit0)% resolved | 12.5% | 12.5% |
| OpenHands Indexreported | Information gathering (GAIA)% resolved | 72.7% | 40.0% |
| OpenHands Indexreported | Issue resolution (SWE-Bench)% resolved | 74.2% | 62.0% |
| OpenHands Indexreported | Testing (SWT-Bench)% resolved | 68.8% | 45.7% |
Bold green marks the better value on that metric. Where a source reports ranges that overlap, the difference may not be meaningful; see the benchmark page for ranges.