dots.llm1.inst: benchmark results
Provider: RedNote. Released 2025-06-06. Access: Open.
Unified ELO 1583 ± 33, rank #700 of 2656 rated models, from 13 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| EComStage - Attitude Classification | 87.74 | Task Score (%) | 96.9 |
| EComStage - Query Rewrite | 79.61 | Task Score (%) | 62.5 |
| EComStage - Query Match | 98.08 | Task Score (%) | 60.9 |
| BenchTable - Reasoning | 38.5 | Weighted Score (%) | 46.9 |
| BenchTable | 44.6 | Total Score (%) | 43.3 |
| BenchTable - Tech | 48.3 | Weighted Score (%) | 42.7 |
| BenchTable - STEM | 46.1 | Weighted Score (%) | 41.9 |
| EComStage - Solution Decision | 74.13 | Task Score (%) | 34.4 |
| EComStage | 78.09 | Task Score (%) | 28.1 |
| BenchTable - Utility | 32.6 | Weighted Score (%) | 20.6 |
| EComStage - RAG-QA | 64.92 | Task Score (%) | 18.8 |
| EComStage - Intent Recognition | 71.4 | Task Score (%) | 15.6 |
Interactive version: theaggregate.ai/model?slug=dots-llm1-inst · How It Works · Data refreshed daily, snapshot 2026-09-19.