Tencent Hy4 trails GPT-6.1 on hard tests as Kimi K3.1 Pro beats it on two benchmarks
heyshrutimishra · x · 2026-11-04
Tencent's Hy4 agent still has notable gaps on hard benchmarks: 19.8 on Terminal Bench Science vs. 60.9 for GPT-6.1 Sol, and Tencent itself admits a "notable gap remains" with top closed models on its hardest tests.
It's also not the top open model across the board: Moonshot's Kimi K3.1 Pro edges it on OSWorld (79.6) and AutomationBench (65.6)—so China now has two open models in this range.
Hy4 weights are coming, Tencent says, with a full system card.
More from Models
- Same leak, reshared: ChatGPT's five family plan prices spotted again — heyshrutimishra · 2026-11-04
- Fable 5.5 delayed as Anthropic reportedly bets OpenAI's Astra 6.2 won't beat it — haider1 · 2026-11-04
- ByteDance open-sources Axion 1.0-35B agent foundation model with full reproducible recipe — pmttyji · 2026-11-04
- Community asks Moonshot when Kimi K3.1 model weights will drop — bgmshana · 2026-11-04
- Meta's Muse Spark Open license counts distilled models as derivatives — aidenclarke_12 · 2026-11-04
- Tencent Hunyuan teases upcoming LMArena debut — TencentHunyuan · 2026-11-04