BELLE-Llama2-13B-chat-0.4M: benchmark results
Provider: Other. Access: Open.
Aggregate Rating 1345 ± 26, rank #7830 of 10916 rated models, from 17 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - HellaSwag | 82.31 | Normalized accuracy (%) (10-shot) | 50.3 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 50.85 | MC2 (%) (0-shot) | 49.7 |
| Open LLM Leaderboard v1 - ARC Challenge | 60.67 | Normalized accuracy (%) (25-shot) | 48.9 |
| Open LLM Leaderboard v1 - WinoGrande | 75.53 | Accuracy (%) (5-shot) | 42.7 |
| Open LLM Leaderboard v1 - MMLU | 55.94 | Accuracy (%) (5-shot) | 37.8 |
| Open LLM Leaderboard v1 - GSM8K | 14.4 | Accuracy (%) (5-shot) | 36.3 |
| LLMEval-Fair - Education | 4.93 | Discipline Score (0-10) | 8.6 |
| LLMEval-Fair - Engineering | 2.57 | Discipline Score (0-10) | 6.9 |
| LLMEval-Fair - Management | 3.8 | Discipline Score (0-10) | 6.9 |
| LLMEval-Fair - Literature | 2.83 | Discipline Score (0-10) | 6 |
| LLMEval-Fair - History | 3.33 | Discipline Score (0-10) | 5.2 |
| LLMEval-Fair - Law | 4.73 | Discipline Score (0-10) | 5.2 |
Interactive version: theaggregate.ai/model?slug=belle-llama2-13b-chat-0-4m · How It Works · Data refreshed daily, snapshot 2026-11-08.