gemma-2B — benchmark results

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

Unified ELO 1249 ± 19, rank #1619 of 1776 rated models, from 171 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open Japanese LLM - ALT J TO E Bleu EN31.09Score (%)98.3
Open Japanese LLM - Wikicorpus J TO E Bleu EN33.83Score (%)97.6
Open Japanese LLM - Wikicorpus E TO J Bleu JA41.92Score (%)96.4
Open Japanese LLM - ALT E TO J Bleu JA23.5Score (%)94.5
EuroEval Finnish NLU - Scandisent FI89.49Sentiment classification Score (%)53.7
Open Japanese LLM - Mbpp Pylint Check32.73Score (%)51.3
Open Japanese LLM - Wiki NER SET F15.31Score (%)51.2
EuroEval Dutch NLU - DBRD86.49Sentiment classification Score (%)49.2
AI Energy Score (Text Generation)4Energy Score (1-5)47.5
EuroEval Faroese NLU - FoSent23.93Sentiment classification Score (%)45.6
EuroEval Italian NLU - Sentipolc1647.86Sentiment classification Score (%)45.5
URIAL-Bench - Math3.3Judge Score (0-10)44.4

Interactive version: theaggregate.ai/model?slug=gemma-2b · How the rankings work · Data refreshed daily, snapshot 2026-07-22.