sherlock-dash-alpha: benchmark results
Provider: Other. Released 2025-11-15. Access: API.
Unified ELO 1671 ± 50, rank #397 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| SpeechMap Compliance | 100 | % Requests Completed | 100 |
| SvelteBench | 92.2 | Average pass@1 (%) | 68.9 |
| EQ-Bench Creative Writing v3 | 1210.8 | Elo | 47.1 |
| NYT Connections Older Models | 12.2 | Score (%) | 45.9 |
| Creative Writing v3 | 1328.9 | Elo score (self-reported) | 42.7 |
| EQ-Bench Longform Writing | 47.2 | Writing Score (0-100) | 30.1 |
| LisanBench | 0.01 | Mean Path Length / Current Maximum | 26.8 |
| Tinybird AI SQL Benchmark - Exactness | 38.24 | Result exactness vs human reference queries (0-100) | 16.3 |
| Tinybird AI SQL Benchmark - First-Attempt Success Rate | 62 | Questions answered with a valid query on the first attempt ( | 10 |
| Tinybird AI SQL Benchmark - Success Rate | 74 | Questions answered with a valid query within 3 retries (%) | 9.2 |
Interactive version: theaggregate.ai/model?slug=sherlock-dash-alpha · How It Works · Data refreshed daily, snapshot 2026-09-19.