Llama-SEA-LION-v3.5-70B-R: benchmark results
Provider: Meta.
Aggregate Rating 1584 ± 37, rank #1192 of 10916 rated models, from 13 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| GoTo-AI Leaderboard - IndoMMLU - STEM | 77.45 | Score (0-100) | 100 |
| GoTo-AI Leaderboard - IndoMMLU | 64.19 | Score (0-100) | 94.4 |
| GoTo-AI Leaderboard - Balinese | 59.94 | Score (0-100) | 88.9 |
| GoTo-AI Leaderboard - Batak Toba | 42.05 | Score (0-100) | 88.9 |
| GoTo-AI Leaderboard - IndoMMLU - Local Languages and Cultures | 40.95 | Score (0-100) | 88.9 |
| GoTo-AI Leaderboard - IndoMMLU - Social Science | 70.3 | Score (0-100) | 88.9 |
| GoTo-AI Leaderboard - IndoMMLU - Indonesian Language | 64.49 | Score (0-100) | 83.3 |
| GoTo-AI Leaderboard - IndoMMLU - Humanities | 70.17 | Score (0-100) | 77.8 |
| FilBench - Cultural Knowledge | 70.4 | Category Score (%) | 73 |
| FilBench - Generation | 14.88 | Category Score (%) | 69.2 |
| FilBench | 55.86 | FilBench Score (%) | 66.7 |
| FilBench - Reading Comprehension | 54.41 | Category Score (%) | 43.2 |
Interactive version: theaggregate.ai/model?slug=llama-sea-lion-v3-5-70b-r · How It Works · Data refreshed daily, snapshot 2026-11-08.