Compare / Claude Haiku 4.5 vs Mistral Medium 3.5
Claude Haiku 4.5 vs Mistral Medium 3.5
62 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 | Mistral Medium 3.5 |
|---|---|---|---|
| BulletBenchmeasured by us | Cost per gameUS dollars | $0.0318 | $0.0261 |
| BulletBenchmeasured by us | Games lost on time% of games | 0.0% | 0.0% |
| BulletBenchmeasured by us | Invalid moves% of moves | 0.9% | 0.4% |
| BulletBenchmeasured by us | Ladder Eloladder Elo | 491 | 555 |
| BulletBenchmeasured by us | Median move timemilliseconds | 1.3 s | 0.5 s |
| BulletBenchmeasured by us | Cost per gameUS dollars | $0.0163 | $0.0354 |
| BulletBenchmeasured by us | Games lost on time% of games | 25.0% | 0.0% |
| BulletBenchmeasured by us | Invalid moves% of moves | 0.3% | 0.4% |
| BulletBenchmeasured by us | Ladder Eloladder Elo | 445 | 572 |
| BulletBenchmeasured by us | Median move timemilliseconds | 1.2 s | 0.5 s |
| BulletBenchmeasured by us | Cost per gameUS dollars | $0.0095 | $0.0297 |
| BulletBenchmeasured by us | Games lost on time% of games | 83.3% | 0.0% |
| BulletBenchmeasured by us | Invalid moves% of moves | 0.0% | 0.0% |
| BulletBenchmeasured by us | Ladder Eloladder Elo | 33 | 529 |
| BulletBenchmeasured by us | Median move timemilliseconds | 1.3 s | 0.5 s |
| CatalogBenchmeasured by us | Channel rules broken% of products | 39.3% | 13.1% |
| CatalogBenchmeasured by us | Content quality% of checks | 94.4% | 93.7% |
| 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 | 6.5% | 10.1% |
| CatalogBenchmeasured by us | Publish-ready listings% of products | 0.0% | 0.0% |
| CatalogBenchmeasured by us | Reliably publish-ready% of products | 0.0% | 0.0% |
| CatalogBenchmeasured by us | Unsupported claimsclaims per product | 14.3 | 9.12 |
| CatalogBenchmeasured by us | Unsupported claims% of products | 99.4% | 100.0% |
| CatalogBenchmeasured by us | Wrong attributes% of products | 51.2% | 36.3% |
| CatalogBenchmeasured by us | Wrong category or variant% of products | 6.5% | 13.1% |
| CatalogBenchmeasured by us | Channel compliance% of products | 76.8% | 95.8% |
| CatalogBenchmeasured by us | Channel rules broken% of products | 23.2% | 4.2% |
| CatalogBenchmeasured by us | Conflicts caught% of conflicts | 100.0% | 90.9% |
| CatalogBenchmeasured by us | Content quality% of checks | 94.6% | 94.5% |
| CatalogBenchmeasured by us | Cost per productUS dollars | $0.0061 | $0.0080 |
| CatalogBenchmeasured by us | Decision accuracy% of decisions | 86.0% | 90.5% |
| CatalogBenchmeasured by us | Failed outputs% of products | 0.0% | 0.0% |
| CatalogBenchmeasured by us | Field accuracy% of missing fields | 93.7% | 91.7% |
| CatalogBenchmeasured by us | Invented values% of filled values | 6.2% | 0.0% |
| CatalogBenchmeasured by us | Missing UK information% of products | 0.0% | 0.0% |
| CatalogBenchmeasured by us | Not findable% of products | 8.9% | 14.3% |
| CatalogBenchmeasured by us | Publish-ready listings% of products | 0.6% | 15.5% |
| CatalogBenchmeasured by us | Reliably publish-ready% of products | 0.0% | 5.4% |
| CatalogBenchmeasured by us | Unsupported claimsclaims per product | 7.92 | 3.07 |
| CatalogBenchmeasured by us | Unsupported claims% of products | 94.0% | 75.6% |
| CatalogBenchmeasured by us | Wrong attributes% of products | 48.2% | 30.9% |
| CatalogBenchmeasured by us | Wrong category or variant% of products | 7.7% | 11.3% |
| ROASBenchmeasured by us | Audience scorescore out of 100 | 30.9 | 28.5 |
| ROASBenchmeasured by us | Business scorescore out of 100 | 7.3 | 3.4 |
| ROASBenchmeasured by us | Consistency scorescore out of 100 | 8.7 | 8.7 |
| ROASBenchmeasured by us | Contribution profitsimulated US dollars | −$205,001 | −$159,882 |
| ROASBenchmeasured by us | Cost of a runUS dollars | $0.0298 | $0.15 |
| ROASBenchmeasured by us | Months over budgetmonths of 12 | 2 | 3 |
| ROASBenchmeasured by us | Overall scorescore out of 100 | 17.5 | 15.2 |
| ROASBenchmeasured by us | Planning scorescore out of 100 | 54.4 | 55.2 |
| ROASBenchmeasured by us | Return on ad spendprofit per $1 spent | −$0.21 | −$0.17 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,418 | 1,430 |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,420 | 1,430 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,387 | 1,398 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,452 | 1,434 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,415 | 1,421 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,414 | 1,426 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,399 | 1,404 |
| UGI Leaderboardreported | Requested-length error% off the requested word count | 6.0% | 18.0% |
| UGI Leaderboardreported | Style adherencescore from 0 to 1 | 0.39 | 0.35 |
| UGI Leaderboardreported | Writing scorescore out of 100 | 52.2 | 45.5 |
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.