Compare / Claude Haiku 4.5 vs Gemini 3.8 Flash
Claude Haiku 4.5 vs Gemini 3.8 Flash
32 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 Haiku 4.5 | Gemini 3.8 Flash |
|---|---|---|---|
| BulletBenchmeasured by us | Ladder Eloladder Elo | 491 | 1,126 |
| BulletBenchmeasured by us | Median move timemilliseconds | 1.3 s | 4.0 s |
| CatalogBenchmeasured by us | Content quality% of checks | 94.4% | 97.3% |
| CatalogBenchmeasured by us | Failed outputs% of products | 0.0% | 0.0% |
| CatalogBenchmeasured by us | Publish-ready listings% of products | 0.0% | 2.4% |
| CatalogBenchmeasured by us | Reliably publish-ready% of products | 0.0% | 1.8% |
| CatalogBenchmeasured by us | Unsupported claimsclaims per product | 14.3 | 7.12 |
| CatalogBenchmeasured by us | Channel compliance% of products | 76.8% | 98.8% |
| CatalogBenchmeasured by us | Conflicts caught% of conflicts | 100.0% | 100.0% |
| CatalogBenchmeasured by us | Content quality% of checks | 94.6% | 97.1% |
| CatalogBenchmeasured by us | Cost per productUS dollars | $0.0061 | $0.0103 |
| CatalogBenchmeasured by us | Decision accuracy% of decisions | 86.0% | 94.3% |
| CatalogBenchmeasured by us | Failed outputs% of products | 0.0% | 0.0% |
| CatalogBenchmeasured by us | Field accuracy% of missing fields | 93.7% | 92.7% |
| CatalogBenchmeasured by us | Invented values% of filled values | 6.2% | 0.2% |
| CatalogBenchmeasured by us | Publish-ready listings% of products | 0.6% | 33.3% |
| CatalogBenchmeasured by us | Reliably publish-ready% of products | 0.0% | 16.1% |
| CatalogBenchmeasured by us | Unsupported claimsclaims per product | 7.92 | 1.79 |
| ROASBenchmeasured by us | Cost of a runUS dollars | $0.0298 | $0.16 |
| ROASBenchmeasured by us | Months over budgetmonths of 12 | 2 | 0 |
| ROASBenchmeasured by us | Overall scorescore out of 100 | 17.5 | 51.4 |
| ROASBenchmeasured by us | Return on ad spendprofit per £1 spent | −£0.21 | £0.65 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,418 | 1,477 |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,420 | 1,482 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,387 | 1,482 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,452 | 1,529 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,415 | 1,488 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,414 | 1,492 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,399 | 1,486 |
| UGI Leaderboardreported | Requested-length error% off the requested word count | 6.0% | 13.0% |
| UGI Leaderboardreported | Style adherencescore from 0 to 1 | 0.39 | 0.34 |
| UGI Leaderboardreported | Writing scorescore out of 100 | 52.2 | 78.5 |
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.