Compare / DeepSeek V3.2 vs GPT-4.1
DeepSeek V3.2 vs GPT-4.1
12 results from 3 sources that measured both models. Each row is in the source's own units; there is no overall winner.
| Benchmark | Metric | DeepSeek V3.2 | GPT-4.1 |
|---|---|---|---|
| Arena (formerly LMArena)reported | OverallArena rating | 1,437 | 1,408 |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,423 | 1,415 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,400 | 1,402 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,453 | 1,405 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,420 | 1,403 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,425 | 1,415 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,410 | 1,405 |
| UGI Leaderboardreported | Requested-length error% off the requested word count | 26.0% | 6.0% |
| UGI Leaderboardreported | Style adherencescore from 0 to 1 | 0.36 | 0.33 |
| UGI Leaderboardreported | Writing scorescore out of 100 | 57.3 | 67.5 |
| Vectara Hallucination Leaderboardreported | Answer rate% of documents | 92.6% | 99.9% |
| Vectara Hallucination Leaderboardreported | Hallucination rate% of summaries | 6.3% | 5.6% |
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.