Compare / GLM 5 vs GLM 5.3
GLM 5 vs GLM 5.3
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 | GLM 5 | GLM 5.3 |
|---|---|---|---|
| Arena (formerly LMArena)reported | OverallArena rating | 1,452 | 1,468 |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,451 | 1,474 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,447 | 1,456 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,481 | 1,516 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,446 | 1,480 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,457 | 1,480 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,447 | 1,470 |
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 27.9 | 44.8 |
| Artificial Analysisreported | GPQA Diamond% of questions | 82.0% | 91.7% |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 29.3% | 42.3% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 75.7% | 79.7% |
| Vending-Bench 2reported | Money after a yearUS dollars | $4,432.12 | $8,163.61 |
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.