Topxtral-4x7B-v0.1: benchmark results
Provider: Other. Released 2024-02-19. Access: Open.
Aggregate Rating 1460 ± 23, rank #913 of 1635 rated models, from 19 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - GSM8K | 71.72 | Accuracy (%) (5-shot) | 96.5 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 73.38 | MC2 (%) (0-shot) | 94.3 |
| Open LLM Leaderboard v1 - ARC Challenge | 72.53 | Normalized accuracy (%) (25-shot) | 92.4 |
| Open LLM Leaderboard v1 - HellaSwag | 88.33 | Normalized accuracy (%) (10-shot) | 91 |
| Open Chinese LLM - TruthfulQA MC | 61.19 | Accuracy (%) | 87.6 |
| Open LLM Leaderboard v1 - WinoGrande | 83.19 | Accuracy (%) (5-shot) | 87.5 |
| Open Portuguese LLM - FaQuAD NLI | 78.02 | Macro F1 (%) | 82.2 |
| Open LLM Leaderboard v1 - MMLU | 64.96 | Accuracy (%) (5-shot) | 79.3 |
| Open Portuguese LLM - ASSIN2 RTE | 92.08 | Macro F1 (%) | 74.2 |
| Open Portuguese LLM - BLUEX | 54.8 | Accuracy (%) | 61.4 |
| Open Portuguese LLM - ENEM | 64.31 | Accuracy (%) | 58.2 |
| Open Chinese LLM - GSM8K | 46.4 | Accuracy (%) | 53.6 |
Interactive version: theaggregate.ai/model?slug=topxtral-4x7b-v0-1 · How It Works · Data refreshed daily, snapshot 2026-11-05.