GeekRadar / The comparison desk
COMPARE.
AI models
tencent

Hunyuan T1 (20250711)

Model evaluation

Capability & preference

Human preference · Arena

Overall text preferences from head-to-head votes. Not factual accuracy or a task-success rate.

Hunyuan T1 (20250711) 1400.7 Hunyuan T1 (20250711) · 95% interval 1392.1–1409.4 · 4,584 votes · 2026-11-08

Recorded results

Only the same benchmark, version, workload, scenario and unit share a row. Missing results are not zero. System results include the full submitted hardware and software configuration.

Arena text preference / chinesehuman preference · 2026-11-08 · rating

Hunyuan T1 (20250711)

1,425.88 rating

Confidence interval: 1,394.56 – 1,457.20

354 votes

Category
chinese
Evaluated configuration
Hunyuan T1 (20250711)
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-11-08 · rating

Hunyuan T1 (20250711)

1,389.04 rating

Confidence interval: 1,369.27 – 1,408.80

805 votes

Category
coding
Evaluated configuration
Hunyuan T1 (20250711)
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-11-08 · rating

Hunyuan T1 (20250711)

1,392.90 rating

Confidence interval: 1,369.17 – 1,416.63

615 votes

Category
creative_writing
Evaluated configuration
Hunyuan T1 (20250711)
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-11-08 · rating

Hunyuan T1 (20250711)

1,396.95 rating

Confidence interval: 1,383.66 – 1,410.24

1883 votes

Category
english
Evaluated configuration
Hunyuan T1 (20250711)
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-11-08 · rating

Hunyuan T1 (20250711)

1,380.17 rating

Confidence interval: 1,367.79 – 1,392.55

3251 votes

Category
exclude_ties
Evaluated configuration
Hunyuan T1 (20250711)
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-11-08 · rating

Hunyuan T1 (20250711)

1,394.81 rating

Confidence interval: 1,357.02 – 1,432.59

216 votes

Category
expert
Evaluated configuration
Hunyuan T1 (20250711)
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-11-08 · rating

Hunyuan T1 (20250711)

1,399.07 rating

Confidence interval: 1,385.99 – 1,412.14

1954 votes

Category
hard_prompts
Evaluated configuration
Hunyuan T1 (20250711)
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-11-08 · rating

Hunyuan T1 (20250711)

1,398.65 rating

Confidence interval: 1,378.14 – 1,419.16

790 votes

Category
hard_prompts_english
Evaluated configuration
Hunyuan T1 (20250711)
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-11-08 · rating

Hunyuan T1 (20250711)

1,372.35 rating

Confidence interval: 1,351.18 – 1,393.52

760 votes

Category
industry_business_and_management_and_financial_operations
Evaluated configuration
Hunyuan T1 (20250711)
Evaluation type
human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-11-08 · rating

Hunyuan T1 (20250711)

1,353.34 rating

Confidence interval: 1,334.02 – 1,372.66

855 votes

Category
industry_entertainment_and_sports_and_media
Evaluated configuration
Hunyuan T1 (20250711)
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-11-08 · rating

Hunyuan T1 (20250711)

1,416.73 rating

Confidence interval: 1,382.97 – 1,450.49

273 votes

Category
industry_legal_and_government
Evaluated configuration
Hunyuan T1 (20250711)
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-11-08 · rating

Hunyuan T1 (20250711)

1,434.17 rating

Confidence interval: 1,412.14 – 1,456.20

721 votes

Category
industry_life_and_physical_and_social_science
Evaluated configuration
Hunyuan T1 (20250711)
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-11-08 · rating

Hunyuan T1 (20250711)

1,392.22 rating

Confidence interval: 1,354.12 – 1,430.31

221 votes

Category
industry_mathematical
Evaluated configuration
Hunyuan T1 (20250711)
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-11-08 · rating

Hunyuan T1 (20250711)

1,453.71 rating

Confidence interval: 1,416.26 – 1,491.16

262 votes

Category
industry_medicine_and_healthcare
Evaluated configuration
Hunyuan T1 (20250711)
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-11-08 · rating

Hunyuan T1 (20250711)

1,408.83 rating

Confidence interval: 1,394.13 – 1,423.54

1521 votes

Category
industry_software_and_it_services
Evaluated configuration
Hunyuan T1 (20250711)
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-11-08 · rating

Hunyuan T1 (20250711)

1,384.16 rating

Confidence interval: 1,365.96 – 1,402.37

1005 votes

Category
industry_writing_and_literature_and_language
Evaluated configuration
Hunyuan T1 (20250711)
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-11-08 · rating

Hunyuan T1 (20250711)

1,375.64 rating

Confidence interval: 1,358.21 – 1,393.08

1105 votes

Category
instruction_following
Evaluated configuration
Hunyuan T1 (20250711)
Evaluation type
human preference
Arena text preference / koreanhuman preference · 2026-11-08 · rating

Hunyuan T1 (20250711)

1,406.07 rating

Confidence interval: 1,360.83 – 1,451.32

183 votes

Category
korean
Evaluated configuration
Hunyuan T1 (20250711)
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-11-08 · rating

Hunyuan T1 (20250711)

1,384.91 rating

Confidence interval: 1,365.65 – 1,404.16

897 votes

Category
longer_query
Evaluated configuration
Hunyuan T1 (20250711)
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-11-08 · rating

Hunyuan T1 (20250711)

1,415.36 rating

Confidence interval: 1,377.00 – 1,453.71

232 votes

Category
math
Evaluated configuration
Hunyuan T1 (20250711)
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-11-08 · rating

Hunyuan T1 (20250711)

1,393.04 rating

Confidence interval: 1,370.90 – 1,415.19

664 votes

Category
multi_turn
Evaluated configuration
Hunyuan T1 (20250711)
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-11-08 · rating

Hunyuan T1 (20250711)

1,394.62 rating

Confidence interval: 1,383.30 – 1,405.93

2641 votes

Category
non_english
Evaluated configuration
Hunyuan T1 (20250711)
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-11-08 · rating

Hunyuan T1 (20250711)

1,400.74 rating

Confidence interval: 1,392.08 – 1,409.40

4584 votes

Category
overall
Evaluated configuration
Hunyuan T1 (20250711)
Evaluation type
human preference
Arena text preference / polishhuman preference · 2026-11-08 · rating

Hunyuan T1 (20250711)

1,386.65 rating

Confidence interval: 1,356.95 – 1,416.35

380 votes

Category
polish
Evaluated configuration
Hunyuan T1 (20250711)
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-11-08 · rating

Hunyuan T1 (20250711)

1,382.36 rating

Confidence interval: 1,351.34 – 1,413.37

304 votes

Category
russian
Evaluated configuration
Hunyuan T1 (20250711)
Evaluation type
human preference

Run it locally

Inference · memory estimate

Hunyuan T1 (20250711)

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Model license
Proprietary