SambaLingo-Thai-Chat: benchmark results
Provider: Other. Access: Open.
Unified ELO 1349 ± 21, rank #2482 of 2928 rated models, from 12 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - HellaSwag | 78.42 | Normalized accuracy (%) (10-shot) | 33.8 |
| Open LLM Leaderboard v1 - GSM8K | 8.57 | Accuracy (%) (5-shot) | 28.7 |
| Open LLM Leaderboard v1 - WinoGrande | 72.22 | Accuracy (%) (5-shot) | 28.6 |
| Open LLM Leaderboard v1 - ARC Challenge | 52.73 | Normalized accuracy (%) (25-shot) | 27.7 |
| HELM ThaiExam - A-Level | 26.77 | EM | 26.8 |
| HELM ThaiExam - ONET | 30.86 | EM | 26.8 |
| Open LLM Leaderboard v1 - MMLU | 43.95 | Accuracy (%) (5-shot) | 23.1 |
| HELM ThaiExam - IC | 28.42 | EM | 15.9 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 40.84 | MC2 (%) (0-shot) | 15.5 |
| HELM ThaiExam - TGAT | 55.38 | EM | 14.6 |
| HELM ThaiExam - ThaiExam | 33.63 | EM | 14.6 |
| HELM ThaiExam - TPAT-1 | 26.72 | EM | 7.3 |
Interactive version: theaggregate.ai/model?slug=sambalingo-thai-chat · How It Works · Data refreshed daily, snapshot 2026-09-23.