tamil-llama-7B-instruct-v0.1: benchmark results
Provider: Other. Access: Open.
Aggregate Rating 1255 ± 35, rank #9210 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - WinoGrande | 70.64 | Accuracy (%) (5-shot) | 25 |
| Open LLM Leaderboard v1 - ARC Challenge | 48.04 | Normalized accuracy (%) (25-shot) | 22.9 |
| Open LLM Leaderboard v1 - HellaSwag | 70.97 | Normalized accuracy (%) (10-shot) | 21.1 |
| Open LLM Leaderboard v1 - MMLU | 39.95 | Accuracy (%) (5-shot) | 21.1 |
| Open LLM Leaderboard v1 - GSM8K | 1.82 | Accuracy (%) (5-shot) | 18.4 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 41.7 | MC2 (%) (0-shot) | 17.9 |
Interactive version: theaggregate.ai/model?slug=tamil-llama-7b-instruct-v0-1 · How It Works · Data refreshed daily, snapshot 2026-11-08.