TheBeagle-v2beta-32B-MGS: benchmark results

Provider: Other. Released 2024-10-20. Access: Open.

Unified ELO 1712 ± 57, rank #307 of 2656 rated models, from 11 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard - MMLU-Pro59.15Score99.7
Open LLM Leaderboard - GPQA40.1Score99.2
Open LLM Leaderboard - BBH70.35Score99.1
Open Portuguese LLM - ASSIN2 RTE94.73Macro F1 (%)98.6
Open LLM Leaderboard - MuSR50.21Score98.5
Open Portuguese LLM - ENEM84.81Accuracy (%)97.8
Open Portuguese LLM - BLUEX78.03Accuracy (%)97.1
Open LLM Leaderboard - MATH Level 549.47Score96.5
Open Portuguese LLM - OAB Exams63.23Accuracy (%)95.8
Open Portuguese LLM - FaQuAD NLI82.27Macro F1 (%)94.1
Open LLM Leaderboard - IFEval51.81Score61.7

Interactive version: theaggregate.ai/model?slug=thebeagle-v2beta-32b-mgs · How It Works · Data refreshed daily, snapshot 2026-09-19.