Llama 3 8B Cpt Sea Lionv2.1 Instruct — benchmark results
Provider: Meta. Access: Open.
Unified ELO 1400 ± 13, rank #1203 of 1756 rated models, from 40 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| SeaEval - Dialogue - SAMSum (Zero-Shot) | 30.5 | Average ROUGE (0-100) | 87.5 |
| SeaEval - Dialogue - DialogSum (Zero-Shot) | 25.38 | Average ROUGE (0-100) | 78.3 |
| SeaEval - Cultural Reasoning - SG-Eval v1 Cleaned (Zero-Shot) | 66.18 | Accuracy (%) | 73.8 |
| SeaEval - FLORES Translation - Vietnamese-to-English (Zero-Shot) | 32.83 | BLEU (0-100) | 69.6 |
| Sahabat-AI - Indonesian (ID) | 54.35 | Score (%) | 62.5 |
| SeaEval - FLORES Translation - Malay-to-English (Zero-Shot) | 39.04 | BLEU (0-100) | 56.5 |
| SeaEval - FLORES Translation - Indonesian-to-English (Zero-Shot) | 38.89 | BLEU (0-100) | 52.2 |
| SeaEval - Cultural Reasoning - PH-Eval (Zero-Shot) | 56 | Accuracy (%) | 43.8 |
| SeaEval - Cultural Reasoning - SG-Eval (Zero-Shot) | 66.02 | Accuracy (%) | 42.9 |
| SeaEval - Cross-Lingual Consistency - Cross-LogiQA (Zero-Shot) | 49.92 | Accuracy (%) | 40.9 |
| SEA LLM Leaderboard - SeaExam | 54.1 | Private Average Score (%) | 40 |
| Sahabat-AI - Indonesian Average | 38.29 | Average Score (%) | 37.5 |
Interactive version: aibenchmarks.dev/model?slug=llama-3-8b-cpt-sea-lionv2-1-instruct · How the rankings work · Data refreshed daily, snapshot 2026-07-17.