Sarashina3
model Your tags
Your notes
SB Intuitions' third-generation flagship series, launched via SoftBank's sovereign cloud "Cloud PF Type A" (Oracle Alloy on domestic data centers): five models — mini (standard), nano, guard (safety classifier), embedding, and rerank. Pretrained from scratch on "30T tokens of large-scale, high-quality data" with curriculum learning; post-training uses multi-stage asynchronous RL plus OPSD (on-policy self-distillation). Evaluated against Qwen3 4B/30B/235B, GPT-4.1, and GPT-5.4 mini on eight benchmarks including ELYZA-tasks-100, AIME 2025, IFBench, BFCL v3, and τ²-bench Telecom. API-only; parameter counts undisclosed.
Model Details
Training tokens 30T
Variants
| Name | Parameters | Notes |
|---|---|---|
| Sarashina3 mini | — | — |
| Sarashina3 nano | — | — |
| Sarashina3 guard | — | — |
| Sarashina3 embedding | — | — |
| Sarashina3 rerank | — | — |