Developer
Tencent
10 indexed models; 2 currently meet the evidence threshold for the overall ranking. Together they have results from 13 evaluations.
Models by Tencent
| Model | Evals | Components | Rank | Release date |
|---|---|---|---|---|
| Hy3 | 6 | 5/7 | 88 | 2026-07-02 |
| Hy3 Preview | 5 | 5/7 | 189 | 2026-04-13 |
| Hunyuan 2.0 Think | 1 | 4/7 | — | 2025-11-09 |
| Hunyuan A13B Instruct | 2 | 5/7 | — | 2025-06-25 |
| Hunyuan Hy3 | 1 | 1/7 | — | 2026-07-06 |
| Hunyuan Large | 1 | 3/7 | — | 2025-02-10 |
| Hunyuan Standard | 1 | 1/7 | — | 2023-09-07 |
| Hunyuan T1 | 2 | 5/7 | — | 2025-08-22 |
| Hunyuan Turbos | 1 | 1/7 | — | 2025-02-27 |
| HY4 Preview | 2 | 1/7 | — | 2026-08-27 |
Evaluations covering Tencent models (13)
AA-Omniscience · Arena Factuality — Text Arena (factuality-only weighting) · BullshitBench v2 · Concordia AI Risk Monitor · DystopiaBench · Enkrypt AI Safety Leaderboard · LiveSecBench · M3-SafetyBench · Opposite-Narrator Sycophancy · Social Welfare Function Benchmark · SpeciEval · TAC · WildClawBench Safety & Alignment (OpenClaw harness)