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
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Nejumi 4 - MT-Bench (Japanese) | 98.56 | Score (%) | 97.4 |
| Nejumi 4 - jaster (2-shot) - KUCI | 93 | Exact match (%) | 97.2 |
| Nejumi 4 - MT-Bench (Japanese) - Roleplay | 99.5 | Judge rating (1-10, x10) | 95 |
| Nejumi 4 - MT-Bench (Japanese) - Extraction | 98.5 | Judge rating (1-10, x10) | 94.7 |
| Nejumi 4 - GLP - Logical Reasoning | 95 | Score (%) | 94 |
| Nejumi 4 - jaster (2-shot) - JNLI | 92 | Exact match (%) | 93.1 |
| Nejumi 4 - GLP - Expression | 99 | Score (%) | 93 |
| Nejumi 4 - Toxicity - Fairness | 99.44 | Criteria met (%) | 92.1 |
| Nejumi 4 - MT-Bench (Japanese) - Humanities | 100 | Judge rating (1-10, x10) | 89.6 |
| Nejumi 4 - jaster (0-shot) - JNLI | 89 | Exact match (%) | 89.3 |
| Nejumi 4 - JBBQ (2-shot) - Accuracy | 94 | Accuracy (%) | 87.4 |
| Nejumi 4 - jaster (2-shot) - JaNLI | 100 | Exact match (%) | 83 |
Interactive version: theaggregate.ai/model?slug=sage-s2-1-flash · How It Works · Data refreshed daily, snapshot 2026-11-20.