Linkbricks-Horizon-AI-Superb-70B: benchmark results

Provider: Other.

Aggregate Rating 1359 ± 39, rank #7470 of 10916 rated models, from 50 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open Japanese LLM - AIO Char F174.02Score (%)87.3
Open Japanese LLM - Niilc Char F156.68Score (%)83.9
Open Japanese LLM - QA56.21Score (%)73.3
Open Japanese LLM - Jsick Exact Match81.79Score (%)70.8
Open Japanese LLM - Wiki NER SET F17.96Score (%)67.4
Open Japanese LLM - Wiki Coreference SET F11.93Score (%)39.4
Open Japanese LLM - Jsem Exact Match74.24Score (%)37.7
Open Japanese LLM - Mbpp Pylint Check7.63Score (%)36.9
Open Japanese LLM - Jmmlu Exact Match53.32Score (%)36.8
Open Japanese LLM - HE57.92Score (%)36.5
Open Japanese LLM - Wiki Reading Char F166.94Score (%)34.9
Open Japanese LLM - MMLU EN Exact Match62.52Score (%)34.1

Interactive version: theaggregate.ai/model?slug=linkbricks-horizon-ai-superb-70b · How It Works · Data refreshed daily, snapshot 2026-11-08.