Compare / DeepSeek V4 Pro 0423 vs GLM 4.6V
DeepSeek V4 Pro 0423 vs GLM 4.6V
14 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 V4 Pro 0423 | GLM 4.6V |
|---|---|---|---|
| Arena (formerly LMArena)reported | OverallArena rating | 1,455 | 1,392 |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,460 | 1,370 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,446 | 1,350 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,480 | 1,394 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,452 | 1,367 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,458 | 1,379 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,451 | 1,357 |
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 36.0 | 11.2 |
| Artificial Analysisreported | GPQA Diamond% of questions | 92.8% | 71.9% |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 41.0% | 9.6% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 80.3% | 48.7% |
| UGI Leaderboardreported | Requested-length error% off the requested word count | 34.0% | 35.0% |
| UGI Leaderboardreported | Style adherencescore from 0 to 1 | 0.36 | 0.39 |
| UGI Leaderboardreported | Writing scorescore out of 100 | 68.4 | 39.7 |
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.