tamil-llama-13B-base-v0.1: benchmark results
Provider: Other. Access: Open.
Aggregate Rating 1327 ± 36, rank #8218 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - WinoGrande | 75.61 | Accuracy (%) (5-shot) | 43.1 |
| Open LLM Leaderboard v1 - HellaSwag | 79.95 | Normalized accuracy (%) (10-shot) | 39.6 |
| Open LLM Leaderboard v1 - MMLU | 52.05 | Accuracy (%) (5-shot) | 31.4 |
| Open LLM Leaderboard v1 - ARC Challenge | 52.82 | Normalized accuracy (%) (25-shot) | 27.9 |
| Open LLM Leaderboard v1 - GSM8K | 0 | Accuracy (%) (5-shot) | 4.5 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 36.56 | MC2 (%) (0-shot) | 3.9 |
Interactive version: theaggregate.ai/model?slug=tamil-llama-13b-base-v0-1 · How It Works · Data refreshed daily, snapshot 2026-11-08.