Dolphin-Mistral-24B-Venice-Edition: benchmark results
Provider: Dolphin. Released 2025-06-12. Access: Open.
Aggregate Rating 1538 ± 49, rank #1850 of 10916 rated models, from 8 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| UGI - Willingness (W/10) | 7.8 | W/10 Score | 81.6 |
| UGI Leaderboard | 40.79 | UGI Score | 67.2 |
| UGI - Natural Intelligence | 24.41 | NatInt Score | 58.3 |
| UGI - Writing | 32.21 | Writing Score | 44.3 |
| Tinybird AI SQL Benchmark - Exactness | 40.47 | Result exactness vs human reference queries (0-100) | 19.9 |
| Tinybird AI SQL Benchmark - Success Rate | 92 | Questions answered with a valid query within 3 retries (%) | 15.8 |
| Tinybird AI SQL Benchmark - First-Attempt Success Rate | 70 | Questions answered with a valid query on the first attempt ( | 11.7 |
| Fucc Boi Bench | 7.5 | Average Fuccboi Score (0-10, lower is better) | 0 |
Interactive version: theaggregate.ai/model?slug=dolphin-mistral-24b-venice-edition · How It Works · Data refreshed daily, snapshot 2026-11-08.