Compare / Claude Sonnet 4.6 vs GLM 5.3
Claude Sonnet 4.6 vs GLM 5.3
19 results from 5 sources that measured both models. Each row is in the source's own units; there is no overall winner.
| Benchmark | Metric | Claude Sonnet 4.6 | GLM 5.3 |
|---|---|---|---|
| APEX-Agentsreported | Tasks passed% of tasks | 43.0% | 56.6% |
| Arena (formerly LMArena)reported | OverallArena rating | 1,461 | 1,468 |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,482 | 1,474 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,449 | 1,456 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,506 | 1,516 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,475 | 1,480 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,472 | 1,480 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,455 | 1,470 |
| Artificial Analysisreported | Artificial Analysis Coding Indexindex score | 63.0 | 74.8 |
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 30.1 | 44.8 |
| Artificial Analysisreported | GPQA Diamond% of questions | 87.5% | 91.7% |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 33.6% | 42.3% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 80.0% | 79.7% |
| Artificial Analysisreported | SciCode% of problems | 50.1% | 59.0% |
| Artificial Analysisreported | Terminal-Bench 2.1% of tasks | 71.2% | 83.9% |
| Artificial Analysisreported | Terminal-Bench 4.0% of tasks | 3.0% | 41.9% |
| Artificial Analysisreported | Τ-bench banking% of tasks | 34.4% | 50.3% |
| SimpleQA Verified (Epoch AI)reported | Correct answers% of questions | 35.5% | 41.0% |
| Vending-Bench 2reported | Money after a yearUS dollars | $7,204.14 | $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.