llm-jp-3-7.2B: benchmark results

Provider: Other. Access: Open.

Unified ELO 1409 ± 47, rank #1829 of 2656 rated models, from 26 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
pfgen-bench - Completion Mode - Truthfulness0.85Truthfulness Score75.9
pfgen-bench - Completion Mode - Fluency0.71Fluency Score75.2
pfgen-bench - Completion Mode - Score0.61pfgen Score (mean of three)74.1
pfgen-bench - Completion Mode - Helpfulness0.26Helpfulness Score73.3
Swallow - Pre-trained Japanese - NIILC60.1Character F1 (%)67.3
Swallow - Pre-trained Japanese - JEMHopQA48.1Character F1 (%)51
Swallow - Pre-trained Japanese - WMT20 En-Ja24.9BLEU49
Swallow - Pre-trained English - XWINO88.8Accuracy (%)45.9
Swallow - Pre-trained Japanese - XL-Sum15.2ROUGE-2 (%)42.9
Swallow - Pre-trained English - TriviaQA52.2Exact Match (%)40.8
Swallow - Pre-trained Japanese - WMT20 Ja-En19BLEU39.8
Swallow - Pre-trained English - HellaSwag54.4Accuracy (%)36.7

Interactive version: theaggregate.ai/model?slug=llm-jp-3-7-2b · How It Works · Data refreshed daily, snapshot 2026-09-19.