Hy-MT2-30B-A3B: benchmark results
Provider: Other. Released 2026-05-21. Access: Open.
Unified ELO 1507 ± 1, rank #1353 of 3078 rated models, from 9 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| IFMTBench | 85.7 | IF$_\text{T}$ (self-reported) | 92.9 |
| BenchmarkList ECI | 110.97 | Capability Index (ECI) | 50.8 |
| Last Translation Benchmark | 2.2 | Verified Translations (%) | 42.9 |
| Tinybird AI SQL Benchmark - First-Attempt Success Rate | 92 | Questions answered with a valid query on the first attempt ( | 40.5 |
| HardMTBench | 88.6 | HardMTBench zh-en GEMBA-DA (self-reported) | 40 |
| LM Market Cap LMC Score | 40 | LMC Score (0-100) | 28 |
| Tinybird AI SQL Benchmark - Success Rate | 96 | Questions answered with a valid query within 3 retries (%) | 24.5 |
| Tinybird AI SQL Benchmark - Exactness | 40.01 | Result exactness vs human reference queries (0-100) | 20.6 |
| AI Chess Leaderboard (Reasoning) | 389 | Elo | 0.9 |
Interactive version: theaggregate.ai/model?slug=hy-mt2-30b-a3b · How It Works · Data refreshed daily, snapshot 2026-09-19.