Compare / Gemini 3.8 Flash vs Mistral Large 4
Gemini 3.8 Flash vs Mistral Large 4
65 results from 4 sources that measured both models. Each row is in the source's own units; there is no overall winner.
| Benchmark | Metric | Gemini 3.8 Flash | Mistral Large 4 |
|---|---|---|---|
| BulletBenchmeasured by us | Cost per gameUS dollars | $0.0795 | $0.0082 |
| BulletBenchmeasured by us | Games lost on time% of games | 12.5% | 0.0% |
| BulletBenchmeasured by us | Invalid moves% of moves | 0.0% | 0.6% |
| BulletBenchmeasured by us | Ladder Eloladder Elo | 1,126 | 555 |
| BulletBenchmeasured by us | Median move timemilliseconds | 4.0 s | 0.8 s |
| BulletBenchmeasured by us | Cost per gameUS dollars | $0.0041 | $0.0117 |
| BulletBenchmeasured by us | Games lost on time% of games | 83.3% | 58.3% |
| BulletBenchmeasured by us | Invalid moves% of moves | 0.0% | 1.8% |
| BulletBenchmeasured by us | Ladder Eloladder Elo | 197 | 249 |
| BulletBenchmeasured by us | Median move timemilliseconds | 1.8 s | 0.8 s |
| CatalogBenchmeasured by us | Channel rules broken% of products | 0.6% | 1.2% |
| CatalogBenchmeasured by us | Claims to check% of products | 5.4% | 3.3% |
| CatalogBenchmeasured by us | Content quality% of checks | 97.6% | 95.9% |
| 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 | 8.9% | 3.0% |
| CatalogBenchmeasured by us | Publish-ready listings% of products | 16.7% | 10.7% |
| CatalogBenchmeasured by us | Reliably publish-ready% of products | 3.6% | 1.8% |
| CatalogBenchmeasured by us | Unsupported claims% of products | 81.5% | 80.4% |
| CatalogBenchmeasured by us | Unsupported claimsclaims per product | 3.08 | 3.69 |
| CatalogBenchmeasured by us | Wrong attributes% of products | 11.9% | 17.3% |
| CatalogBenchmeasured by us | Wrong category or variant% of products | 3.0% | 1.8% |
| CatalogBenchmeasured by us | Channel compliance% of products | 99.4% | 100.0% |
| CatalogBenchmeasured by us | Channel rules broken% of products | 0.6% | 3.0% |
| CatalogBenchmeasured by us | Claims to check% of products | 0.0% | 0.7% |
| CatalogBenchmeasured by us | Conflicts caught% of conflicts | 100.0% | 100.0% |
| CatalogBenchmeasured by us | Content quality% of checks | 97.7% | 96.5% |
| CatalogBenchmeasured by us | Cost per productUS dollars | $0.0103 | $0.0033 |
| CatalogBenchmeasured by us | Decision accuracy% of decisions | 96.4% | 93.1% |
| CatalogBenchmeasured by us | Failed outputs% of products | 0.0% | 0.0% |
| CatalogBenchmeasured by us | Field accuracy% of missing fields | 92.7% | 94.4% |
| CatalogBenchmeasured by us | Invented values% of filled values | 0.2% | 3.5% |
| CatalogBenchmeasured by us | Missing UK information% of products | 0.0% | 0.0% |
| CatalogBenchmeasured by us | Not findable% of products | 8.3% | 4.2% |
| CatalogBenchmeasured by us | Publish-ready listings% of products | 54.8% | 39.9% |
| CatalogBenchmeasured by us | Reliably publish-ready% of products | 35.7% | 10.7% |
| CatalogBenchmeasured by us | Unsupported claimsclaims per product | 0.79 | 0.91 |
| CatalogBenchmeasured by us | Unsupported claims% of products | 31.6% | 33.3% |
| CatalogBenchmeasured by us | Wrong attributes% of products | 15.5% | 19.6% |
| CatalogBenchmeasured by us | Wrong category or variant% of products | 3.6% | 1.2% |
| DeckBenchmeasured by us | Accurate decks% of tasks | 16.7% | 0.0% |
| DeckBenchmeasured by us | Caveat dropped% of tasks | 0.0% | 16.7% |
| DeckBenchmeasured by us | Clean layout% of tasks | 16.7% | 33.3% |
| DeckBenchmeasured by us | Cost per deckUS dollars | $0.0613 | $0.0148 |
| DeckBenchmeasured by us | Deck ratingrating | 904 | 515 |
| DeckBenchmeasured by us | Design quality% of the maximum | 61.7% | 30.5% |
| DeckBenchmeasured by us | Draft figure quoted% of tasks | 50.0% | 16.7% |
| DeckBenchmeasured by us | Findings missing% of tasks | 0.0% | 0.0% |
| DeckBenchmeasured by us | Head-to-head win rate% of comparisons | 42.9% | 10.7% |
| DeckBenchmeasured by us | Layout defects% of tasks | 83.3% | 66.7% |
| DeckBenchmeasured by us | Misleading metric used% of tasks | 0.0% | 0.0% |
| DeckBenchmeasured by us | Presentable decks% of tasks | 0.0% | 0.0% |
| DeckBenchmeasured by us | Recommendation late or wrong% of tasks | 33.3% | 83.3% |
| DeckBenchmeasured by us | Slides needing work% of tasks | 33.3% | 100.0% |
| DeckBenchmeasured by us | Unsupported claims% of tasks | 50.0% | 50.0% |
| DeckBenchmeasured by us | Unsupported numbers% of tasks | 16.7% | 33.3% |
| ROASBenchmeasured by us | Audience scorescore out of 100 | 67.1 | 55.8 |
| ROASBenchmeasured by us | Business scorescore out of 100 | 51.0 | 34.2 |
| ROASBenchmeasured by us | Consistency scorescore out of 100 | 36.4 | 16.7 |
| ROASBenchmeasured by us | Contribution profitsimulated US dollars | $842,432 | $533,401 |
| ROASBenchmeasured by us | Cost of a runUS dollars | $0.16 | $0.0657 |
| ROASBenchmeasured by us | Months over budgetmonths of 12 | 0 | 0 |
| ROASBenchmeasured by us | Overall scorescore out of 100 | 51.4 | 37.0 |
| ROASBenchmeasured by us | Planning scorescore out of 100 | 54.7 | 55.0 |
| ROASBenchmeasured by us | Return on ad spendprofit per $1 spent | $0.65 | $0.45 |
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.