recurrentgemma-9B-it: benchmark results
Provider: Google. Released 2024-06-07. Access: Open.
Aggregate Rating 1410 ± 39, rank #5610 of 10916 rated models, from 34 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard - MuSR | 43.79 | Score | 76.8 |
| Open PL LLM - EQ-Bench | 42.43 | EQ-Bench Score | 69.2 |
| Open PL LLM - PolEmo2-IN (multiple choice, 5-shot) | 79.78 | Accuracy (%) | 63.6 |
| Open PL LLM - PolEmo2-IN (generative, 5-shot) | 78.25 | Accuracy (%) | 60.6 |
| Open LLM Leaderboard - IFEval | 50.1 | Score | 59.2 |
| Open PL LLM - RAG | 60.39 | Average RAG Score (%) | 57.7 |
| Open PL LLM - PolQA Reranking (multiple choice, 5-shot) | 72.05 | Accuracy (%) | 57.5 |
| Open PL LLM - PoQuAD Open Book (generative, 5-shot) | 63.05 | Levenshtein Similarity (%) | 53.3 |
| Polish EQ-Bench | 52.82 | EQ-Bench Score (parseability-adjusted) | 50.5 |
| Open PL LLM - CBD (generative, 5-shot) | 22.6 | Macro F1 (%) | 45.8 |
| Open PL LLM - PolQA Open Book (generative, 5-shot) | 78.05 | Levenshtein Similarity (%) | 44.2 |
| Open PL LLM - DYK (multiple choice, 5-shot) | 43.89 | Binary F1 (%) | 40.6 |
Interactive version: theaggregate.ai/model?slug=recurrentgemma-9b-it · How It Works · Data refreshed daily, snapshot 2026-11-08.