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

BenchmarkScoreMetricPercentile
IFMTBench85.7IF$_\text{T}$ (self-reported)92.9
BenchmarkList ECI110.97Capability Index (ECI)50.8
Last Translation Benchmark2.2Verified Translations (%)42.9
Tinybird AI SQL Benchmark - First-Attempt Success Rate92Questions answered with a valid query on the first attempt (40.5
HardMTBench88.6HardMTBench zh-en GEMBA-DA (self-reported)40
LM Market Cap LMC Score40LMC Score (0-100)28
Tinybird AI SQL Benchmark - Success Rate96Questions answered with a valid query within 3 retries (%)24.5
Tinybird AI SQL Benchmark - Exactness40.01Result exactness vs human reference queries (0-100)20.6
AI Chess Leaderboard (Reasoning)389Elo0.9

Interactive version: theaggregate.ai/model?slug=hy-mt2-30b-a3b · How It Works · Data refreshed daily, snapshot 2026-09-19.