QwQenSeek-coder: benchmark results

Provider: Alibaba. Access: Open.

Aggregate Rating 1556 ± 35, rank #1612 of 10916 rated models, from 50 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open Japanese LLM - Jmmlu Exact Match76.33Score (%)96.9
Open Japanese LLM - HE78.31Score (%)96.2
Open Japanese LLM - RC92.31Score (%)93.4
Open Japanese LLM - MMLU EN Exact Match80.29Score (%)92.3
Open Japanese LLM - SUM11.67Score (%)90.4
Open Japanese LLM - Xlsum JA Rouge211.68Score (%)90.4
Open Japanese LLM - Xlsum JA RougeLsum27.12Score (%)89.9
Open Japanese LLM - Jnli Exact Match89.07Score (%)89.4
Open Japanese LLM - Xlsum JA Bert Score JA F170.67Score (%)88.8
Open Japanese LLM - Xlsum JA Rouge132.02Score (%)88.7
Open Japanese LLM - Wikicorpus E TO J Bleu JA13.69Score (%)86.5
Open Japanese LLM - Jsts Pearson90.17Score (%)85.6

Interactive version: theaggregate.ai/model?slug=qwqenseek-coder · How It Works · Data refreshed daily, snapshot 2026-11-08.