openbuddy-llama3-8B-v21.2-32k: benchmark results
Provider: OpenBuddy. Released 2024-06-18. Access: Open.
Aggregate Rating 1439 ± 40, rank #4219 of 10916 rated models, from 14 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard - IFEval | 61.92 | Score | 74.1 |
| Open Chinese LLM - C-Eval Semantic | 74.59 | Accuracy (%) | 64.2 |
| Open Chinese LLM - CMMLU | 55.02 | Accuracy (%) | 59.2 |
| Open Chinese LLM Leaderboard | 57.96 | Official Nonzero-Task Mean (%) | 58.1 |
| Open Chinese LLM - GSM8K | 45.49 | Accuracy (%) | 48.5 |
| Open LLM Leaderboard - MMLU-Pro | 32.99 | Score | 46.1 |
| Open LLM Leaderboard - BBH | 48.56 | Score | 42.9 |
| Open Chinese LLM - TruthfulQA MC | 52.86 | Accuracy (%) | 42.2 |
| Open LLM Leaderboard - MATH Level 5 | 7.85 | Score | 40.4 |
| Open Chinese LLM - ARC Challenge | 48.72 | Accuracy (%) | 35.9 |
| Open Chinese LLM - HellaSwag | 57.72 | Accuracy (%) | 34.3 |
| Open LLM Leaderboard - GPQA | 27.94 | Score | 34.2 |
Interactive version: theaggregate.ai/model?slug=openbuddy-llama3-8b-v21-2-32k · How It Works · Data refreshed daily, snapshot 2026-11-08.