SEAL - Spanish: leaderboard
Spanish-language tasks covering practical assistance, writing, reasoning, and culturally situated scenarios, measuring fluency and cultural appropriateness in Spanish.
Metric: Score. Source: scale.com. Saturation forecast: Estimated already saturated. 22 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | O1 (2024-12-17) | 1134 | #149 |
| 2 | Gemini 2.0 Flash | 1119 | #342 |
| 3 | O1 Preview | 1111 | #193 |
| 4 | Gemini 2.0 Flash (Thinking) | 1108 | #342 (Gemini 2.0 Flash) |
| 5 | Gemini 1.5 Pro | 1105 | #445 |
| 6 | GPT-4o (2024-05-13) | 1084 | #325 |
| 7 | O3 Mini | 1079 | #272 |
| 8 | Gemini 1.5 Pro (0514) | 1069 | #512 |
| 9 | GPT-4o (2024-08-06) | 1067 | #336 |
| 10 | GPT-4 | 1034 | #438 |
| 11 | Mistral Large 2 (Jul) | 1032 | #484 |
| 12 | GPT-4 Turbo (Preview) | 1020 | #397 |
| 13 | Claude 3.5 Sonnet (20240620) | 992 | #299 |
| 14 | aya-expanse-32B | 983 | #692 |
| 15 | Gemini 1.5 Flash | 980 | #618 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=seal-spanish · How It Works · Data refreshed daily, snapshot 2026-10-20.