Xwin-LM-13B-V0.2: benchmark results

Provider: Other. Access: Open.

Aggregate Rating 1411 ± 46, rank #5572 of 10916 rated models, from 9 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open Portuguese LLM - OAB Exams41.37Accuracy (%)46.9
Open Portuguese LLM - BLUEX48.96Accuracy (%)43.9
Open Portuguese LLM - ENEM57.45Accuracy (%)41.9
pfgen-bench - QA Mode - Fluency0.53Fluency Score39.4
pfgen-bench - QA Mode - Score0.43pfgen Score (mean of three)34.5
Open Portuguese LLM - FaQuAD NLI51.38Macro F1 (%)32.9
pfgen-bench - QA Mode - Truthfulness0.67Truthfulness Score32.7
Open Portuguese LLM - ASSIN2 RTE81.93Macro F1 (%)32.5
pfgen-bench - QA Mode - Helpfulness0.09Helpfulness Score30.3

Interactive version: theaggregate.ai/model?slug=xwin-lm-13b-v0-2 · How It Works · Data refreshed daily, snapshot 2026-11-08.