Confucius-o1-14B: benchmark results

Provider: Other. Access: Open.

Aggregate Rating 1564 ± 33, rank #1501 of 10916 rated models, from 56 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard - MATH Level 543.13Score92.3
Open LLM Leaderboard - MMLU-Pro52.65Score91.7
Open LLM Leaderboard - GPQA36.49Score91.6
Open Japanese LLM - SUM11.51Score (%)89.4
Open Japanese LLM - Xlsum JA Rouge211.51Score (%)89.4
Open Japanese LLM - Xlsum JA RougeLsum26.69Score (%)88.7
Open Japanese LLM - Xlsum JA Rouge131.56Score (%)87
Open LLM Leaderboard - BBH63Score86.7
Open Japanese LLM - Xlsum JA Bert Score JA F170.43Score (%)85.6
Open Japanese LLM - Jnli Exact Match87.1Score (%)85.3
Open Japanese LLM - RC91.68Score (%)84.1
Open Japanese LLM - Wiki Coreference SET F16.95Score (%)81.2

Interactive version: theaggregate.ai/model?slug=confucius-o1-14b · How It Works · Data refreshed daily, snapshot 2026-11-08.