Sage-S2.1-Flash: benchmark results

Provider: Shanghai AI Lab. Access: Open.

Aggregate Rating 1751 ± 26, rank #179 of 10489 rated models, from 96 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Nejumi 4 - MT-Bench (Japanese)98.56Score (%)97.4
Nejumi 4 - jaster (2-shot) - KUCI93Exact match (%)97.2
Nejumi 4 - MT-Bench (Japanese) - Roleplay99.5Judge rating (1-10, x10)95
Nejumi 4 - MT-Bench (Japanese) - Extraction98.5Judge rating (1-10, x10)94.7
Nejumi 4 - GLP - Logical Reasoning95Score (%)94
Nejumi 4 - jaster (2-shot) - JNLI92Exact match (%)93.1
Nejumi 4 - GLP - Expression99Score (%)93
Nejumi 4 - Toxicity - Fairness99.44Criteria met (%)92.1
Nejumi 4 - MT-Bench (Japanese) - Humanities100Judge rating (1-10, x10)89.6
Nejumi 4 - jaster (0-shot) - JNLI89Exact match (%)89.3
Nejumi 4 - JBBQ (2-shot) - Accuracy94Accuracy (%)87.4
Nejumi 4 - jaster (2-shot) - JaNLI100Exact match (%)83

Interactive version: theaggregate.ai/model?slug=sage-s2-1-flash · How It Works · Data refreshed daily, snapshot 2026-11-20.