Compare / DeepSeek V3.2 vs GLM 4.6
DeepSeek V3.2 vs GLM 4.6
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 | GLM 4.6 |
|---|---|---|---|
| Arena (formerly LMArena)reported | OverallArena rating | 1,437 | 1,447 |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,423 | 1,412 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,400 | 1,400 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,453 | 1,439 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,420 | 1,412 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,425 | 1,424 |
| 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% | 13.0% |
| UGI Leaderboardreported | Style adherencescore from 0 to 1 | 0.36 | 0.38 |
| UGI Leaderboardreported | Writing scorescore out of 100 | 57.3 | 53.3 |
| Vectara Hallucination Leaderboardreported | Answer rate% of documents | 92.6% | 94.5% |
| Vectara Hallucination Leaderboardreported | Hallucination rate% of summaries | 6.3% | 9.5% |
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.