gemma-7B (IT): benchmark results
Provider: Google. Released 2024-02-21. Access: Open.
Unified ELO 1355 ± 1, rank #1257 of 1392 rated models, from 224 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| LLM Trustworthy - Stereotype | 100 | Trust Score (%) | 94 |
| Fin-Bias | 97.6 | Average Herding Score (with rating) (self-reported) | 83.3 |
| Open CoT - LogiQA | 6.55 | CoT Gain (%) | 82.1 |
| Open LLM Leaderboard - MuSR | 12.53 | Score | 68.6 |
| LLM Trustworthy - Privacy | 83.69 | Trust Score (%) | 68 |
| LLM Trustworthy - Toxicity | 75.52 | Trust Score (%) | 68 |
| Enkrypt AI - Bias Risk | 79.59 | Risk Score | 65.3 |
| SALAD-Bench | 54.81 | Average Safety Score (%) | 60.6 |
| SALAD-Bench Base | 94.08 | Safety Score (%) | 60.6 |
| LLM Trustworthy - Fairness | 93.88 | Trust Score (%) | 60 |
| InfiBench | 40.68 | Score (%) | 58.1 |
| LLM Trustworthy Leaderboard | 66.87 | Average Trust Score (%) | 56 |
Interactive version: theaggregate.ai/model?slug=gemma-7b-it · How It Works · Data refreshed daily, snapshot 2026-09-05.