WestLake-7B-v2 — benchmark results

Community creator senseable's Mistral-based WestLake v2, a 7B tune aimed at role-play consistency and creative writing. Provider: Other. Released 2024-01-22. Access: Open.

Unified ELO 1435 ± 22, rank #1070 of 1776 rated models, from 26 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
EuroEval Spanish NLU - Sentiment Headlines ES45.49Sentiment classification Score (%)71.4
EuroEval Italian NLU - MultiNERD IT69.6Named entity recognition Score (%)70.7
EuroEval Italian NLU - SQuAD IT69.38Reading comprehension Score (%)65.1
EuroEval Norwegian Knowledge27.91Knowledge Average Score (%)64.8
EuroEval Italian NLU52.92NLU Average Score (%)63.7
EuroEval Italian NLU - Sentipolc1654.85Sentiment classification Score (%)62.4
EuroEval Spanish NLU - CoNLL ES64.53Named entity recognition Score (%)62.4
EuroEval Spanish Common Sense Reasoning49.19Common Sense Reasoning Average Score (%)59.9
EuroEval Italian48.4Average Score (%)57.1
EuroEval Spanish43.84Average Score (%)56.9
EuroEval Italian Common Sense Reasoning43.15Common Sense Reasoning Average Score (%)56.4
EuroEval Spanish NLU44.26NLU Average Score (%)56.3

Interactive version: theaggregate.ai/model?slug=westlake-7b-v2 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.