gemma-3-1B-pt Base: benchmark results

Provider: Google. Released 2025-03-12. Access: Open.

Unified ELO 1278 ± 19, rank #2523 of 2656 rated models, from 402 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
LA Leaderboard - xStoryCloze Basque53.21Accuracy (%)82.4
LA Leaderboard - WiC Basque50.14Accuracy (%)80.9
LA Leaderboard - XNLI Basque39.45Accuracy (%)80.9
AI Energy Score (Text Generation)5Energy Score (1-5)79.5
LA Leaderboard - WNLI Catalan59.15Accuracy (%)72.8
LA Leaderboard - HumorQA58.82Accuracy (%)70.6
LA Leaderboard - QNLI Basque52.94Accuracy (%)70.6
EuroEval Catalan NLU - Guia CAT59.88Sentiment classification Score (%)62.1
LA Leaderboard - EpecKorrefBin Basque52.64Accuracy (%)61
LA Leaderboard - WNLI Spanish57.75Accuracy (%)61
EuroEval Finnish NLU - Scandisent FI89.97Sentiment classification Score (%)60.9
EuroEval Hungarian NLU - HuSST46.8Sentiment classification Score (%)59.4

Interactive version: theaggregate.ai/model?slug=gemma-3-1b-pt-base · How It Works · Data refreshed daily, snapshot 2026-09-19.