recoilme-gemma-2-9B-v0.4: benchmark results
recoilme's lightly documented Gemma 2 9B variant, notable mainly as a popular base for downstream community merges. Provider: Other. Released 2024-09-18. Access: Open.
Aggregate Rating 1567 ± 17, rank #553 of 1656 rated models, from 144 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-EQ-Bench | 61.43 | EQ-Bench score | 99.7 |
| Open Ko-LLM Leaderboard | 53.97 | Average (%) | 99.3 |
| Open Korean LLM Leaderboard | 53.97 | Average Score (%) | 99.3 |
| Open Korean LLM - KorNAT-CKA | 39.31 | Normalized accuracy (%) | 98.4 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 69.37 | Exact match, flexible extract (%) | 98 |
| Open Arabic LLM - Aratrust Privacy | 98.25 | Accuracy (%) | 97.2 |
| Open Korean LLM - Ko-IFEval | 62.64 | Strict accuracy, prompt/instruction mean (%) | 97.2 |
| Open Arabic LLM - Alghafa Multiple Choice Grounded Statement Soqal Task | 94 | Accuracy (%) | 93.5 |
| Open LLM Leaderboard - MuSR | 47.27 | Score | 92.2 |
| Open Portuguese LLM - ENEM | 76.35 | Accuracy (%) | 89.9 |
| Open Portuguese LLM - ASSIN2 RTE | 93.46 | Macro F1 (%) | 89.7 |
| Open Portuguese LLM - OAB Exams | 56.22 | Accuracy (%) | 89.6 |
Interactive version: theaggregate.ai/model?slug=recoilme-gemma-2-9b-v0-4 · How It Works · Data refreshed daily, snapshot 2026-10-20.