Tencent Hunyuan HY4 Openly Shares Internal Evals, Admits Math Gap vs Frontier
teortaxesTex · x · 2026-11-05
Tencent's Hunyuan HY4 release included unusually candid internal research evals, revealing a sizable gap in math/science capabilities against frontier models. AI researcher account teortaxesTex endorsed the assessment, noting the frontier is 'in another galaxy' and Tencent has long wanted better math results — a rare case of a lab openly publishing its own weaknesses.
More from Models
- Cognition launches SWE-2 Flash, a 276B-A12B coding model that beats all US open-weight rivals — carlesgelada · 2026-11-05
- Kimi K3.1 Pro (2.8T params, 104B active) lands on Ollama Cloud with zero data retention — ollama · 2026-11-05
- Linear CEO Karri Saarinen: time to retire the word "context" in AI — round · 2026-11-05
- Codex on the $20 plan runs dry after about 2.5-3 hours of nonstop work — tristanbob · 2026-11-05
- Morph launches Reflex: first decision model with cached pricing, 10-20x cheaper than Jev — GabGarrett · 2026-11-05
- Hamel Husain: Benchmarks are used like credit scores, so criticism is warranted — HamelHusain · 2026-11-05