Compare / Claude Fable 5.1 vs Claude Haiku 4.5
Claude Fable 5.1 vs Claude Haiku 4.5
53 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 Fable 5.1 | Claude Haiku 4.5 |
|---|---|---|---|
| BulletBenchmeasured by us | Cost per gameUS dollars | $0.38 | $0.0318 |
| BulletBenchmeasured by us | Games lost on time% of games | 37.5% | 0.0% |
| BulletBenchmeasured by us | Invalid moves% of moves | 0.0% | 0.9% |
| BulletBenchmeasured by us | Ladder Eloladder Elo | 358 | 491 |
| BulletBenchmeasured by us | Median move timemilliseconds | 5.4 s | 1.3 s |
| CatalogBenchmeasured by us | Channel rules broken% of products | 0.6% | 22.6% |
| CatalogBenchmeasured by us | Content quality% of checks | 97.0% | 94.2% |
| CatalogBenchmeasured by us | Failed outputs% of products | 0.0% | 0.0% |
| CatalogBenchmeasured by us | Missing UK information% of products | 0.0% | 0.0% |
| CatalogBenchmeasured by us | Not findable% of products | 1.8% | 6.5% |
| CatalogBenchmeasured by us | Publish-ready listings% of products | 10.1% | 1.2% |
| CatalogBenchmeasured by us | Reliably publish-ready% of products | 1.8% | 0.0% |
| CatalogBenchmeasured by us | Unsupported claimsclaims per product | 3.96 | 7.30 |
| CatalogBenchmeasured by us | Unsupported claims% of products | 86.9% | 95.8% |
| CatalogBenchmeasured by us | Wrong attributes% of products | 14.9% | 51.2% |
| CatalogBenchmeasured by us | Wrong category or variant% of products | 1.8% | 6.5% |
| CatalogBenchmeasured by us | Channel compliance% of products | 100.0% | 92.3% |
| CatalogBenchmeasured by us | Channel rules broken% of products | 0.0% | 7.7% |
| CatalogBenchmeasured by us | Conflicts caught% of conflicts | 100.0% | 100.0% |
| CatalogBenchmeasured by us | Content quality% of checks | 97.4% | 94.9% |
| CatalogBenchmeasured by us | Cost per productUS dollars | $0.0991 | $0.0061 |
| CatalogBenchmeasured by us | Decision accuracy% of decisions | 95.8% | 89.3% |
| CatalogBenchmeasured by us | Failed outputs% of products | 0.0% | 0.0% |
| CatalogBenchmeasured by us | Field accuracy% of missing fields | 94.7% | 93.7% |
| CatalogBenchmeasured by us | Invented values% of filled values | 0.7% | 6.2% |
| CatalogBenchmeasured by us | Missing UK information% of products | 0.0% | 0.0% |
| CatalogBenchmeasured by us | Not findable% of products | 1.8% | 8.9% |
| CatalogBenchmeasured by us | Publish-ready listings% of products | 47.0% | 7.7% |
| CatalogBenchmeasured by us | Reliably publish-ready% of products | 26.8% | 1.8% |
| CatalogBenchmeasured by us | Unsupported claims% of products | 48.2% | 80.4% |
| CatalogBenchmeasured by us | Unsupported claimsclaims per product | 1.23 | 3.50 |
| CatalogBenchmeasured by us | Wrong attributes% of products | 11.9% | 48.2% |
| CatalogBenchmeasured by us | Wrong category or variant% of products | 2.4% | 7.7% |
| ROASBenchmeasured by us | Audience scorescore out of 100 | 67.7 | 30.9 |
| ROASBenchmeasured by us | Business scorescore out of 100 | 52.3 | 7.3 |
| ROASBenchmeasured by us | Consistency scorescore out of 100 | 33.3 | 8.7 |
| ROASBenchmeasured by us | Contribution profitsimulated US dollars | $965,271 | −$205,001 |
| ROASBenchmeasured by us | Cost of a runUS dollars | $2.49 | $0.0298 |
| ROASBenchmeasured by us | Months over budgetmonths of 12 | 0 | 2 |
| ROASBenchmeasured by us | Overall scorescore out of 100 | 51.5 | 17.5 |
| ROASBenchmeasured by us | Planning scorescore out of 100 | 54.6 | 54.4 |
| ROASBenchmeasured by us | Return on ad spendprofit per $1 spent | $0.64 | −$0.21 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,493 | 1,419 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,501 | 1,418 |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,485 | 1,420 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,484 | 1,387 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,516 | 1,452 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,497 | 1,415 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,501 | 1,414 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,496 | 1,399 |
| UGI Leaderboardreported | Requested-length error% off the requested word count | 3.0% | 6.0% |
| UGI Leaderboardreported | Style adherencescore from 0 to 1 | 0.43 | 0.39 |
| UGI Leaderboardreported | Writing scorescore out of 100 | 63.9 | 52.2 |
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.