Tencent Hunyuan / 腾讯混元 · Released 2026-10-26
A specialist bidirectional Chinese-English simultaneous speech-translation model with about 30B total and 3B active parameters, open-sourced under Apache-2.0 (third-party components keep their terms) alongside Interleave and FP8/GGUF variants. Vendor results (~3-second RealSI lag, 85.8% against human interpreters) use GEMBA judged by GPT-6.1-Sol; speech output needs a separate TTS. Simultaneous interpreting differs from AA text intelligence, Pi coding and Physics video continuation, so no same-identity score currently qualifies it for those boards.
Original model explanation ↗No comparable leaderboard score is included yet. Explore the evaluations and examples below.
Vendor evaluation with our reading · not our test
A 30B-total, 3B-active Chinese–English simultaneous speech-translation model goes open source under Apache-2.0: on the long-audio RealSI set its ~3-second lag is the lowest in the vendor chart while outscoring most commercial interpreting APIs; across 18 recordings in ten domains it scores 85.8% against 77.9%/72.1% for CATTI Level 1/2 interpreters, at 3.3s versus 4.5/4.7s.
Official repository · released October 26, read October 27
Official model entry · not downloaded or run
Long-term memory-writing research learns what to retain, update and consolidate within memory frameworks. Its four-harness results use fixed 20% benchmark subsamples and do not establish a general-capability rank.
Original release ↗The 30B-A3B Chinese-English simultaneous speech-translation model opens under Apache-2.0, with FP8/GGUF variants for two bases. Vendor results show ~3-second RealSI lag and 85.8% in the human comparison; they differ from the AA/Pi/Physics board methods.
Original release ↗