recoilme-gemma-2-9B-v0.3: benchmark results
recoilme's community Gemma 2 9B fine-tune (v0.3). Provider: Other. Released 2024-09-18. Access: Open.
Aggregate Rating 1559 ± 19, rank #590 of 1661 rated models, from 21 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Ko-LLM Leaderboard | 52.42 | Average (%) | 98.7 |
| Open Korean LLM Leaderboard | 52.42 | Average Score (%) | 98.7 |
| Open Korean LLM - Ko-IFEval | 66.01 | Strict accuracy, prompt/instruction mean (%) | 98.4 |
| Open Korean LLM - Ko-EQ-Bench | 58.38 | EQ-Bench score | 97.8 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 66.94 | Exact match, flexible extract (%) | 96.5 |
| Open Portuguese LLM - ASSIN2 RTE | 93.87 | Macro F1 (%) | 93 |
| Open Korean LLM - KorNAT-CKA | 33.12 | Normalized accuracy (%) | 90.7 |
| Open LLM Leaderboard - IFEval | 74.39 | Score | 89.4 |
| Open LLM Leaderboard - MuSR | 46.32 | Score | 89 |
| Open Portuguese LLM - ENEM | 75.23 | Accuracy (%) | 88.9 |
| Open Portuguese LLM - FaQuAD NLI | 79.5 | Macro F1 (%) | 87.3 |
| Open Korean LLM - KorNAT-Helpful | 50.48 | Normalized accuracy (%) | 86.1 |
Interactive version: theaggregate.ai/model?slug=recoilme-gemma-2-9b-v0-3 · How It Works · Data refreshed daily, snapshot 2026-10-23.