Volare — benchmark results

Moxoff's Italian-language SFT/LoRA fine-tune of Google's Gemma-7B, trained on SQuAD-it and in-house data for RAG and context-heavy tasks. Provider: Other. Released 2024-04-15. Access: Open.

Unified ELO 1415 ± 12, rank #1154 of 1776 rated models, from 19 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Pinocchio Italian - Lingua Straniera72.56Accuracy (%)79.5
Pinocchio Italian - Matematica E Scienze50.96Accuracy (%)75
Pinocchio Italian Leaderboard55.14Average Accuracy (%)61.4
Pinocchio Italian - Cultura58.69Accuracy (%)59.1
Pinocchio Italian - Generale55.83Accuracy (%)59.1
Pinocchio Italian - Logica41.83Accuracy (%)59.1
Pinocchio Italian - Diritto50.97Accuracy (%)54.5
Open Italian LLM - MMLU-Pro (IT)23.61Accuracy (%)53.6
EVALITA - lexical-substitution28CPS51.1
EVALITA - evalita NER31.55CPS38.3
EVALITA - summarization-fanpage23.28CPS29.8
EVALITA - sentiment-analysis68.39CPS27.7

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