TowerBase-7B-v0.1: benchmark results
Provider: Other. Access: Open.
Unified ELO 1349 ± 21, rank #2483 of 2928 rated models, from 11 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - GSM8K | 13.12 | Accuracy (%) (5-shot) | 35 |
| Open Portuguese LLM - OAB Exams | 35.22 | Accuracy (%) | 32.2 |
| Open LLM Leaderboard v1 - HellaSwag | 77.68 | Normalized accuracy (%) (10-shot) | 31.6 |
| Open Portuguese LLM - ENEM | 36.81 | Accuracy (%) | 28.5 |
| Open LLM Leaderboard v1 - WinoGrande | 72.06 | Accuracy (%) (5-shot) | 28.1 |
| Open Portuguese LLM - BLUEX | 30.6 | Accuracy (%) | 26.4 |
| Open Portuguese LLM - FaQuAD NLI | 44.61 | Macro F1 (%) | 25.5 |
| Open LLM Leaderboard v1 - ARC Challenge | 51.02 | Normalized accuracy (%) (25-shot) | 25.4 |
| Open LLM Leaderboard v1 - MMLU | 43.48 | Accuracy (%) (5-shot) | 22.7 |
| Open Portuguese LLM - ASSIN2 RTE | 36.74 | Macro F1 (%) | 10.7 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 37.29 | MC2 (%) (0-shot) | 5.4 |
Interactive version: theaggregate.ai/model?slug=towerbase-7b-v0-1 · How It Works · Data refreshed daily, snapshot 2026-09-23.