FuseChat-7B-VaRM: benchmark results
Provider: FuseAI. Access: Open.
Unified ELO 1475 ± 19, rank #1513 of 2928 rated models, from 12 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Portuguese LLM - FaQuAD NLI | 78.73 | Macro F1 (%) | 85.4 |
| Open Portuguese LLM - ASSIN2 RTE | 92.73 | Macro F1 (%) | 82.8 |
| Open LLM Leaderboard v1 - GSM8K | 63.46 | Accuracy (%) (5-shot) | 76.9 |
| Open LLM Leaderboard v1 - WinoGrande | 79.16 | Accuracy (%) (5-shot) | 67.7 |
| Open LLM Leaderboard v1 - HellaSwag | 84.25 | Normalized accuracy (%) (10-shot) | 64.9 |
| Open LLM Leaderboard v1 - MMLU | 63.71 | Accuracy (%) (5-shot) | 62.7 |
| Open Portuguese LLM - BLUEX | 54.94 | Accuracy (%) | 61.9 |
| Open LLM Leaderboard v1 - ARC Challenge | 62.88 | Normalized accuracy (%) (25-shot) | 60.2 |
| Open Portuguese LLM - ENEM | 64.8 | Accuracy (%) | 59.9 |
| Open Portuguese LLM - OAB Exams | 41.82 | Accuracy (%) | 49.6 |
| YALL Nous Leaderboard | 52.3 | Average | 47.5 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 45.67 | MC2 (%) (0-shot) | 31.8 |
Interactive version: theaggregate.ai/model?slug=fusechat-7b-varm · How It Works · Data refreshed daily, snapshot 2026-09-23.