Hunyuan T1

Released
2025-03-21
Last refreshed
2026-10-20
Status
Researched 8d ago
Open weightsCommercial use: restrictedLong contextChina

Hunyuan T1 is a released long context model with open-weight and 256K context; evaluate it while provider pricing coverage matures.

Tencent AI Lab releases · 12 in the last 12 months · this family litChangelog →
Specifications
Family
Hunyuan
Released
2025-03-21
Context
256K
Parameters
52B
Architecture
Dense + MoE Hybrid
Openness
Open weights
Weights
Unknown
Code
Unknown
Training
Pretrained
Created by
Tencent AI Lab

AI innovations for societal improvement

Shenzhen, China
Founded 2016
Website
Pricing

No tracked provider pricing is available yet.

Links
Website

About

Tencent Hunyuan T1 is a deep-thinking reasoning model released March 21, 2025. Built on Hunyuan TurboS base, using a Hybrid-Transformer-Mamba MoE architecture — the first ultra-large-scale Mamba-powered LLM with 16 total experts and 52B activated parameters via dynamic routing. 96.7% of compute allocated to reinforcement learning post-training. Benchmarks: MATH-500 96.2, LiveCodeBench 64.9, GPQA Diamond 69.3, MMLU-PRO 87.2 (second only to o1). Decoding speed 2× faster than comparable transformer models. 256K token context. Available on Tencent Cloud API. Source: https://tencent.github.io/llm.hunyuan.T1/README_EN.html

Providers

No active provider routes are tracked for this model yet.

Capabilities

Reasoning

Benchmark peer barsfor Long context

No task-mapped benchmark peers are available for this model yet.

Benchmark scores(1)

Scores are benchmark-specific and are direction-aware: the same numeric gap can mean very different outcomes across suites. Use the leaderboard context and this model's provider route to decide whether the winning margin is meaningful for your workload.
BenchmarkScoreVersionEvaluationSource
LMArena Text Arena - Creative Writing
1393.0text creative_writing 2026-10-22Observed 2026-10-22
Configuration: Hunyuan T1 (20250711)
Harness: LMArena blind pairwise human votes, Bradley-Terry
Evaluator: LMArena
Confidence: confirmed
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Hunyuan T1 (20250711)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 111 of 416, rating 1393.1 (95% CI 1369.4-1416.9), 616 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Source

Source: LMArena (lmarena.ai), CC BY 4.0

Migration checks

No linked migration route is available for this model yet.

API versions

tencent-hunyuan-t1Tencent Hunyuan T1