Compare / GPT-5.2 vs GLM 5.3
GPT-5.2 vs GLM 5.3
14 results from 4 sources that measured both models. Each row is in the source's own units; there is no overall winner.
| Benchmark | Metric | GPT-5.2 | GLM 5.3 |
|---|---|---|---|
| Arena (formerly LMArena)reported | OverallArena rating | 1,442 | 1,468 |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,444 | 1,474 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,391 | 1,456 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,475 | 1,516 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,427 | 1,480 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,437 | 1,480 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,411 | 1,470 |
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 30.4 | 44.8 |
| Artificial Analysisreported | GPQA Diamond% of questions | 90.3% | 91.7% |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 37.7% | 42.3% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 82.7% | 79.7% |
| Artificial Analysisreported | Τ-bench banking% of tasks | 11.1% | 50.3% |
| SimpleQA Verified (Epoch AI)reported | Correct answers% of questions | 37.1% | 41.0% |
| Vending-Bench 2reported | Money after a yearUS dollars | $3,591.33 | $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.