mt5-xl — benchmark results
Provider: Google. Released 2020-10-22. Access: API.
Unified ELO 1167 ± 64, rank #1724 of 1776 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard - MuSR | 5.04 | Score | 24.7 |
| Open LLM Leaderboard - GPQA | 1.9 | Score | 18.3 |
| Open LLM Leaderboard - IFEval | 19.6 | Score | 11.3 |
| Open LLM Leaderboard - BBH | 3.28 | Score | 6.4 |
| Open PL LLM - RAG | 0.08 | Average RAG Score (%) | 5.6 |
| Open PL LLM - Generative | -28.91 | Average Generative Score (%) | 4.9 |
| Open PL LLM Leaderboard | -27.94 | Average Score (%) | 4.9 |
| Open PL LLM - Multiple Choice | -26.68 | Average Multiple-Choice Score (%) | 3.5 |
| Open LLM Leaderboard - MMLU-Pro | 1.33 | Score | 3.2 |
| Open LLM Leaderboard - MATH Level 5 | 0 | Score | 1.3 |
Interactive version: theaggregate.ai/model?slug=mt5-xl · How the rankings work · Data refreshed daily, snapshot 2026-07-22.