Compare / GPT-6 Luna vs GLM 5.2
GPT-6 Luna vs GLM 5.2
17 results from 3 sources that measured both models. Each row is in the source's own units; there is no overall winner.
| Benchmark | Metric | GPT-6 Luna | GLM 5.2 |
|---|---|---|---|
| Arena (formerly LMArena)reported | Confirmed task successIPS effect estimate | 0.05 | 0.04 |
| Arena (formerly LMArena)reported | Praise over complaintIPS effect estimate | -0.03 | 0.10 |
| Arena (formerly LMArena)reported | SteerabilityIPS effect estimate | 0.02 | 0.04 |
| Arena (formerly LMArena)reported | Tool groundingIPS effect estimate | 0.00 | 0.00 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,422 | 1,463 |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,452 | 1,463 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,403 | 1,455 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,505 | 1,500 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,443 | 1,470 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,442 | 1,476 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,415 | 1,459 |
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 38.1 | 33.7 |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 38.5% | 41.1% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 83.3% | 78.3% |
| Artificial Analysisreported | SciCode% of problems | 54.6% | 51.2% |
| Artificial Analysisreported | Terminal-Bench 4.0% of tasks | 12.6% | 1.0% |
| SimpleQA Verified (Epoch AI)reported | Correct answers% of questions | 41.4% | 34.2% |
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.