Virtuoso-Lite — benchmark results
Arcee AI's 10B model built on Falcon3-10B and distilled from DeepSeek-V3 logits. Provider: Arcee AI. Released 2025-01-28. Access: Open.
Unified ELO 1573 ± 24, rank #556 of 1776 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard - IFEval | 81 | Score | 98.4 |
| Open LLM Leaderboard - MuSR | 17.54 | Score | 88.9 |
| French LLM Leaderboard - IFEval FR | 64.1 | Score (%) | 87 |
| Open LLM Leaderboard - GPQA | 12.53 | Score | 85.8 |
| Open LLM Leaderboard - BBH | 43.9 | Score | 83.4 |
| French LLM Leaderboard - GPQA FR | 37.18 | Score (%) | 83.3 |
| Open LLM Leaderboard - MMLU-Pro | 38.23 | Score | 82.4 |
| French LLM Leaderboard - Average | 46.8 | Average Score (%) | 81.5 |
| Open LLM Leaderboard - MATH Level 5 | 25.3 | Score | 78.3 |
| French LLM Leaderboard - BAC FR | 39.12 | Score (%) | 74.1 |
Interactive version: theaggregate.ai/model?slug=virtuoso-lite · How the rankings work · Data refreshed daily, snapshot 2026-07-22.