Compare / trinity-large-preview vs Command R+ (08-2024)
trinity-large-preview vs Command R+ (08-2024)
11 results from 3 sources that measured both models. Each row is in the source's own units; there is no overall winner.
| Benchmark | Metric | trinity-large-preview | Command R+ (08-2024) |
|---|---|---|---|
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,381 | 1,271 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,352 | 1,263 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,403 | 1,250 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,370 | 1,254 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,379 | 1,276 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,359 | 1,277 |
| UGI Leaderboardreported | Requested-length error% off the requested word count | 24.0% | 28.0% |
| UGI Leaderboardreported | Style adherencescore from 0 to 1 | 0.40 | 0.34 |
| UGI Leaderboardreported | Writing scorescore out of 100 | 40.7 | 32.3 |
| Vectara Hallucination Leaderboardreported | Answer rate% of documents | 99.0% | 95.0% |
| Vectara Hallucination Leaderboardreported | Hallucination rate% of summaries | 6.9% | 6.9% |
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.