Overall score
45.0
Rank #65 · B confidence
Tencent · stable
Tencent Hy Team open-weight MoE (295B total / 21B active) with hybrid reasoning, 256K context, and Apache 2.0 weights released July 2026.
Overall score
45.0
Rank #65 · B confidence
Capability
54.7
7 eligible benchmark families
Coverage
62%
Confidence B
Benchmarks scored
7
7 raw result rows
Model specification
Identity, configuration and price are preserved as dated source records.
Category profile
A category remains Not evaluated until an eligible source-qualified result is attached.
Benchmark scores
Best published score per benchmark. Open any row for the full per-benchmark leaderboard.
| Benchmark | Category | Score | Date |
|---|---|---|---|
| GPQA DiamondRanking weighted | reasoning | 90.4% | 2026-07-06 |
| SWE-bench VerifiedRanking weighted | coding | 78% | 2026-07-06 |
| SWE-Bench ProRanking weighted | coding | 57.9% | 2026-07-06 |
| Terminal-BenchRanking weighted | agents | 54.4% | 2026-07-20 |
| Humanity's Last ExamRanking weighted | reasoning | 53.2% | 2026-07-06 |
| GDPval-AA v2Ranking weighted | agents | 35.7% | 2026-07-20 |
| APEX-Agents-AARanking weighted | agents | 25.6% | 2026-07-06 |
Price and efficiency
Operational values are shown only when the source publishes a comparable measurement or a valid derivation.
Verification summary
News and X posts are structurally excluded from this model's evidence graph.
Missing publication dimensions: value. The last source check for this exact model was 2026-07-16.
Related models
Exact variants remain separate even when they share a provider or family.