Dots3-Note (Preview): benchmark results
Provider: Other. Released 2026-08-14. Access: Open.
Unified ELO 1623 ± 1, rank #492 of 3078 rated models, from 9 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| BenchLM | 64.1 | Overall Score | 81.2 |
| Humanity's Last Exam (Self-Reported, With Tools) | 52.6 | Accuracy (%) | 70 |
| WideResearch (BenchLM) | 78.9 | Task Score (%) | 64.3 |
| Tinybird AI SQL Benchmark - Success Rate | 98 | Questions answered with a valid query within 3 retries (%) | 35.5 |
| LM Market Cap LMC Score | 40 | LMC Score (0-100) | 28 |
| LLM2014 Logic 2026-08 | 12.95 | Median Score | 20.5 |
| LLM2014 Logic 2026-09 | 10.32 | Median Score | 18.8 |
| Tinybird AI SQL Benchmark - Exactness | 39.27 | Result exactness vs human reference queries (0-100) | 18.1 |
| Tinybird AI SQL Benchmark - First-Attempt Success Rate | 66 | Questions answered with a valid query on the first attempt ( | 11.5 |
Interactive version: theaggregate.ai/model?slug=dots3-note-preview · How It Works · Data refreshed daily, snapshot 2026-09-19.