Hy3-preview (Non-reasoning) — benchmark results
Tencent Hunyuan Hy3 preview (295B A21B open MoE) evaluated with reasoning disabled. Provider: Tencent. Released 2026-04-24. Access: Open.
Unified ELO 1650 ± 26, rank #366 of 1776 rated models, from 40 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| UGI - Natural Intelligence | 37.5 | NatInt Score | 86.1 |
| AA Omniscience - Software Engineering (SWE) - Go | 46 | Accuracy (%) | 85 |
| UGI Leaderboard | 45.07 | UGI Score | 80.7 |
| AA Omniscience - Software Engineering (SWE) - Julia | 32 | Accuracy (%) | 80.6 |
| UGI - Writing | 41.55 | Writing Score | 78.5 |
| AA Terminal-Bench Hard | 31.82 | Accuracy (%) | 75.3 |
| AA Omniscience - Software Engineering (SWE) - PHP | 40 | Accuracy (%) | 75 |
| AA Omniscience - Software Engineering (SWE) - TypeScript | 38.89 | Accuracy (%) | 74 |
| AA Omniscience - Software Engineering (SWE) - Dart | 30 | Accuracy (%) | 73.5 |
| AA Omniscience - Software Engineering (SWE) - R | 24 | Accuracy (%) | 72 |
| Artificial Analysis Intelligence Index | 26.1 | Intelligence Index | 70.8 |
| AA SciCode | 39.35 | Accuracy (%) | 70.4 |
Interactive version: theaggregate.ai/model?slug=hy3-preview-non-reasoning · How the rankings work · Data refreshed daily, snapshot 2026-07-22.