Compare / Qwen3.8 Max (0902) vs GPT-6 Luna
Qwen3.8 Max (0902) vs GPT-6 Luna
48 results from 3 sources that measured both models. Each row is in the source's own units; there is no overall winner.
| Benchmark | Metric | Qwen3.8 Max (0902) | GPT-6 Luna |
|---|---|---|---|
| CatalogBenchmeasured by us | Channel rules broken% of products | 3.0% | 0.0% |
| CatalogBenchmeasured by us | Content quality% of checks | 93.3% | 97.8% |
| CatalogBenchmeasured by us | Failed outputs% of products | 3.6% | 0.0% |
| CatalogBenchmeasured by us | Missing UK information% of products | 0.0% | 0.0% |
| CatalogBenchmeasured by us | Not findable% of products | 1.8% | 10.1% |
| CatalogBenchmeasured by us | Publish-ready listings% of products | 10.1% | 69.0% |
| CatalogBenchmeasured by us | Reliably publish-ready% of products | 1.8% | 55.4% |
| CatalogBenchmeasured by us | Unsupported claimsclaims per product | 4.58 | 0.32 |
| CatalogBenchmeasured by us | Unsupported claims% of products | 83.3% | 7.7% |
| CatalogBenchmeasured by us | Wrong attributes% of products | 19.6% | 19.1% |
| CatalogBenchmeasured by us | Wrong category or variant% of products | 2.4% | 0.0% |
| CatalogBenchmeasured by us | Channel compliance% of products | 100.0% | 100.0% |
| CatalogBenchmeasured by us | Channel rules broken% of products | 0.6% | 0.0% |
| CatalogBenchmeasured by us | Conflicts caught% of conflicts | 100.0% | 100.0% |
| CatalogBenchmeasured by us | Content quality% of checks | 94.2% | 97.3% |
| CatalogBenchmeasured by us | Cost per productUS dollars | $0.0256 | $0.0005 |
| CatalogBenchmeasured by us | Decision accuracy% of decisions | 93.4% | 97.1% |
| CatalogBenchmeasured by us | Failed outputs% of products | 3.6% | 0.0% |
| CatalogBenchmeasured by us | Field accuracy% of missing fields | 90.3% | 93.7% |
| CatalogBenchmeasured by us | Invented values% of filled values | 2.7% | 1.7% |
| CatalogBenchmeasured by us | Missing UK information% of products | 0.0% | 0.0% |
| CatalogBenchmeasured by us | Not findable% of products | 3.6% | 10.1% |
| CatalogBenchmeasured by us | Publish-ready listings% of products | 53.0% | 66.7% |
| CatalogBenchmeasured by us | Reliably publish-ready% of products | 33.9% | 55.4% |
| CatalogBenchmeasured by us | Unsupported claims% of products | 22.6% | 9.5% |
| CatalogBenchmeasured by us | Unsupported claimsclaims per product | 0.64 | 0.30 |
| CatalogBenchmeasured by us | Wrong attributes% of products | 21.4% | 18.4% |
| CatalogBenchmeasured by us | Wrong category or variant% of products | 1.8% | 1.8% |
| ROASBenchmeasured by us | Audience scorescore out of 100 | 39.7 | 68.2 |
| ROASBenchmeasured by us | Business scorescore out of 100 | 15.6 | 54.8 |
| ROASBenchmeasured by us | Consistency scorescore out of 100 | 19.2 | 35.8 |
| ROASBenchmeasured by us | Contribution profitsimulated US dollars | $99,775 | $738,878 |
| ROASBenchmeasured by us | Cost of a runUS dollars | $0.73 | $0.0142 |
| ROASBenchmeasured by us | Months over budgetmonths of 12 | 2 | 0 |
| ROASBenchmeasured by us | Overall scorescore out of 100 | 25.4 | 53.4 |
| ROASBenchmeasured by us | Planning scorescore out of 100 | 54.8 | 54.8 |
| ROASBenchmeasured by us | Return on ad spendprofit per $1 spent | $0.09 | $0.66 |
| Arena (formerly LMArena)reported | Confirmed task successIPS effect estimate | 0.05 | 0.05 |
| Arena (formerly LMArena)reported | Praise over complaintIPS effect estimate | 0.04 | -0.03 |
| Arena (formerly LMArena)reported | SteerabilityIPS effect estimate | 0.02 | 0.02 |
| Arena (formerly LMArena)reported | Tool groundingIPS effect estimate | -0.01 | 0.00 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,471 | 1,422 |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,480 | 1,452 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,467 | 1,403 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,510 | 1,505 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,472 | 1,443 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,479 | 1,442 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,472 | 1,415 |
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.