Tara-3.8B-v1.1: benchmark results
Provider: Sakalti. Access: Open.
Aggregate Rating 1421 ± 33, rank #5143 of 10916 rated models, from 56 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard - MuSR | 47.8 | Score | 94 |
| Open Japanese LLM - Xlsum JA Rouge1 | 35.36 | Score (%) | 93.6 |
| Open Japanese LLM - Xlsum JA RougeLsum | 28.79 | Score (%) | 92.9 |
| Open Japanese LLM - Xlsum JA Bert Score JA F1 | 70.67 | Score (%) | 88.8 |
| Open Japanese LLM - SUM | 11.4 | Score (%) | 87.9 |
| Open Japanese LLM - Xlsum JA Rouge2 | 11.4 | Score (%) | 87.9 |
| Open LLM Leaderboard - MATH Level 5 | 11.56 | Score | 52.3 |
| Open LLM Leaderboard - GPQA | 29.45 | Score | 49.7 |
| Open Japanese LLM - Jsts Pearson | 87.81 | Score (%) | 48.2 |
| Open Japanese LLM - Wiki NER SET F1 | 4.42 | Score (%) | 45.8 |
| Open LLM Leaderboard - MMLU-Pro | 32.81 | Score | 45.4 |
| Open LLM Leaderboard - BBH | 48.86 | Score | 43.9 |
Interactive version: theaggregate.ai/model?slug=tara-3-8b-v1-1 · How It Works · Data refreshed daily, snapshot 2026-11-08.