# Scale Labs SEAL Spanish (SEAL Spanish)

> Scale's SEAL leaderboard for Spanish: expert raters judge how well models answer about 1,000 prompts written by native Spanish speakers. BenchLM shows it as display-only reference data, excluded from rankings. Scale marked this board deprecated as of March 2025 and no longer adds models.

Canonical page: https://benchlm.ai/benchmarks/scale-spanish

- Category: [external](/external)
- Last updated: November 12, 2026 snapshot

## About SEAL Spanish

- Year: 2026
- Tasks: About 1,000 prompts per language
- Format: Elo-style rating
- Difficulty: External agent and model evaluation
- Paper: [Scale Labs leaderboard](https://labs.scale.com/leaderboard/spanish)

Single-turn prompts across general and culturally specific scenarios, rated by native-speaking experts. Scores are ratings on an Elo-style scale built from expert human comparisons, so only the gaps between rows carry meaning. BenchLM mirrors 22 published rows captured on November 12, 2026 snapshot.

SEAL Spanish is currently displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.

## Leaderboard (22 models)

| Rank | Model | Creator | Score |
|------|-------|---------|-------|
| 1 | [Gemini 2.0 Pro (December 2024)](https://labs.scale.com/leaderboard/spanish) | Google | 1176 |
| 2 | [o1 (December 2024)](https://labs.scale.com/leaderboard/spanish) | OpenAI | 1134 |
| 3 | [Gemini Pro Flash 2](https://labs.scale.com/leaderboard/spanish) | Google | 1119 |
| 4 | [o1-preview](/models/o1-preview) | OpenAI | 1111 |
| 5 | [Gemini 2.0 Flash Thinking (January 2025)](https://labs.scale.com/leaderboard/spanish) | Google | 1108 |
| 6 | [Gemini 1.5 Pro (November 2024)](https://labs.scale.com/leaderboard/spanish) | Google | 1105 |
| 7 | [GPT-4o (May 2024)](https://labs.scale.com/leaderboard/spanish) | OpenAI | 1084 |
| 8 | [o3-mini](/models/o3-mini) | OpenAI | 1079 |
| 9 | [Gemini 1.5 Pro (May 2024)](https://labs.scale.com/leaderboard/spanish) | Google | 1069 |
| 10 | [Gemini 1.5 Pro (August 27, 2024)](https://labs.scale.com/leaderboard/spanish) | Google | 1067 |
| 11 | [GPT-4o (August 2024)](https://labs.scale.com/leaderboard/spanish) | OpenAI | 1067 |
| 12 | [GPT-4 (November 2024)](https://labs.scale.com/leaderboard/spanish) | OpenAI | 1034 |
| 13 | [Mistral Large 2](/models/mistral-large-2) | Mistral | 1032 |
| 14 | [GPT-4 Turbo Preview](https://labs.scale.com/leaderboard/spanish) | OpenAI | 1020 |
| 15 | [Gemini 1.5 Pro (April 2024)](https://labs.scale.com/leaderboard/spanish) | Google | 1005 |
| 16 | [Claude 3.5 Sonnet (June 2024)](https://labs.scale.com/leaderboard/spanish) | Anthropic | 992 |
| 17 | [Aya Expanse 32B](https://labs.scale.com/leaderboard/spanish) | Cohere | 983 |
| 18 | [Gemini 1.5 Flash](/models/gemini-1-5-flash) | Google | 980 |
| 19 | [Gemma 2 27B](/models/gemma-2-27b) | Google | 951 |
| 20 | [Llama 3.2 90B Vision Instruct](https://labs.scale.com/leaderboard/spanish) | Meta | 944 |
| 21 | [Claude 3 Opus](/models/claude-3-opus) | Anthropic | 919 |
| 22 | [Llama 3.1 405B Instruct](https://labs.scale.com/leaderboard/spanish) | Meta | 915 |

## FAQ

### What does SEAL Spanish measure?

Scale's SEAL leaderboard for Spanish: expert raters judge how well models answer about 1,000 prompts written by native Spanish speakers. BenchLM shows it as display-only reference data, excluded from rankings. Scale marked this board deprecated as of March 2025 and no longer adds models.

### Which model leads the published SEAL Spanish snapshot?

Gemini 2.0 Pro (December 2024) currently leads the published SEAL Spanish snapshot with a score of 1176.

### How many models are evaluated on SEAL Spanish?

The November 12, 2026 snapshot contains 22 AI models.

### Does SEAL Spanish affect BenchLM's overall score?

Not directly. SEAL Spanish is still displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.