calme-2.1-qwen2-7B: benchmark results
MaziyarPanahi's general-purpose fine-tune of Qwen2 7B, trained on OpenHermes-2.5, Orca math word problems, and HelpSteer2 to lift benchmark scores. Provider: MaziyarPanahi. Released 2024-06-27. Access: Open.
Aggregate Rating 1455 ± 19, rank #974 of 1661 rated models, from 21 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-GSM8K (flexible extract) | 57.01 | Exact match, flexible extract (%) | 91.3 |
| Open Korean LLM Leaderboard | 43.41 | Average Score (%) | 87.9 |
| Open Ko-LLM Leaderboard | 43.41 | Average (%) | 87.8 |
| Open Portuguese LLM - ASSIN2 RTE | 92.79 | Macro F1 (%) | 83.7 |
| Open Korean LLM - Ko-EQ-Bench | 32.91 | EQ-Bench score | 82.5 |
| Open LLM Leaderboard - MuSR | 44.37 | Score | 80.2 |
| Open LLM Leaderboard - MATH Level 5 | 23.11 | Score | 76.6 |
| Open Portuguese LLM - FaQuAD NLI | 76.42 | Macro F1 (%) | 76.4 |
| Open Korean LLM - KorNAT-Helpful | 48.93 | Normalized accuracy (%) | 74.9 |
| Open Korean LLM - Ko-IFEval | 33.61 | Strict accuracy, prompt/instruction mean (%) | 67.7 |
| Open Portuguese LLM - BLUEX | 55.22 | Accuracy (%) | 62.5 |
| Open Portuguese LLM - ENEM | 65.15 | Accuracy (%) | 60.6 |
Interactive version: theaggregate.ai/model?slug=calme-2-1-qwen2-7b · How It Works · Data refreshed daily, snapshot 2026-10-23.