gemma-7B — benchmark results

Provider: Google. Released 2024-02-21. Access: Open.

Unified ELO 1249 ± 29, rank #1618 of 1776 rated models, from 225 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open Japanese LLM - ALT J TO E Bleu EN42.39Score (%)99.5
Open Japanese LLM - Wikicorpus J TO E Bleu EN54.2Score (%)98.8
Open Japanese LLM - Wikicorpus E TO J Bleu JA50.33Score (%)96.9
Open Japanese LLM - ALT E TO J Bleu JA25.85Score (%)95.7
European LLM Leaderboard - Zero-Shot Accuracy56.69Average Accuracy (%)95.1
EuroEval Icelandic NLU - NQII56.97Reading comprehension Score (%)90.1
EuroEval French NLU - FQuAD72.77Reading comprehension Score (%)87.7
EuroEval German NLU - Germanquad64.31Reading comprehension Score (%)87.2
Open Medical LLM - MMLU College Biology79.86Accuracy (%)85.5
EuroEval Norwegian NLU - Norquad72.02Reading comprehension Score (%)85.1
EuroEval Spanish NLU - MLQA ES65.03Reading comprehension Score (%)83.1
EuroEval Dutch NLU - SQuAD NL77.24Reading comprehension Score (%)82.7

Interactive version: theaggregate.ai/model?slug=gemma-7b · How the rankings work · Data refreshed daily, snapshot 2026-07-22.