GeekRadar / The comparison desk
COMPARE.
AI models
tencent

hunyuan-standard-256k

Model evaluation

Capability & preference

Human preference · Arena

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

hunyuan-standard-256k 1201.9 hunyuan-standard-256k · 95% interval 1190.3–1213.4 · 2,728 votes · 2026-10-15

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 · 2026-10-15 · rating

hunyuan-standard-256k

1,241.53 rating

Confidence interval: 1,207.59 – 1,275.46

305 votes

Category
chinese
Evaluated configuration
hunyuan-standard-256k
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating

hunyuan-standard-256k

1,230.54 rating

Confidence interval: 1,206.29 – 1,254.80

497 votes

Category
coding
Evaluated configuration
hunyuan-standard-256k
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating

hunyuan-standard-256k

1,164.92 rating

Confidence interval: 1,136.40 – 1,193.44

357 votes

Category
creative_writing
Evaluated configuration
hunyuan-standard-256k
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating

hunyuan-standard-256k

1,214.86 rating

Confidence interval: 1,198.80 – 1,230.93

1278 votes

Category
english
Evaluated configuration
hunyuan-standard-256k
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating

hunyuan-standard-256k

1,079.25 rating

Confidence interval: 1,061.02 – 1,097.49

1812 votes

Category
exclude_ties
Evaluated configuration
hunyuan-standard-256k
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating

hunyuan-standard-256k

1,218.00 rating

Confidence interval: 1,197.80 – 1,238.20

700 votes

Category
hard_prompts
Evaluated configuration
hunyuan-standard-256k
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating

hunyuan-standard-256k

1,227.78 rating

Confidence interval: 1,200.10 – 1,255.47

370 votes

Category
hard_prompts_english
Evaluated configuration
hunyuan-standard-256k
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating

hunyuan-standard-256k

1,177.75 rating

Confidence interval: 1,146.71 – 1,208.78

328 votes

Category
industry_business_and_management_and_financial_operations
Evaluated configuration
hunyuan-standard-256k
Evaluation type
human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating

hunyuan-standard-256k

1,152.85 rating

Confidence interval: 1,124.45 – 1,181.25

379 votes

Category
industry_entertainment_and_sports_and_media
Evaluated configuration
hunyuan-standard-256k
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating

hunyuan-standard-256k

1,200.52 rating

Confidence interval: 1,175.86 – 1,225.18

538 votes

Category
industry_life_and_physical_and_social_science
Evaluated configuration
hunyuan-standard-256k
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating

hunyuan-standard-256k

1,243.23 rating

Confidence interval: 1,212.11 – 1,274.35

292 votes

Category
industry_mathematical
Evaluated configuration
hunyuan-standard-256k
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating

hunyuan-standard-256k

1,222.30 rating

Confidence interval: 1,201.79 – 1,242.81

737 votes

Category
industry_software_and_it_services
Evaluated configuration
hunyuan-standard-256k
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating

hunyuan-standard-256k

1,173.38 rating

Confidence interval: 1,152.80 – 1,193.95

752 votes

Category
industry_writing_and_literature_and_language
Evaluated configuration
hunyuan-standard-256k
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating

hunyuan-standard-256k

1,201.67 rating

Confidence interval: 1,184.92 – 1,218.43

1098 votes

Category
instruction_following
Evaluated configuration
hunyuan-standard-256k
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating

hunyuan-standard-256k

1,224.25 rating

Confidence interval: 1,198.09 – 1,250.41

414 votes

Category
longer_query
Evaluated configuration
hunyuan-standard-256k
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating

hunyuan-standard-256k

1,234.60 rating

Confidence interval: 1,206.16 – 1,263.03

361 votes

Category
math
Evaluated configuration
hunyuan-standard-256k
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating

hunyuan-standard-256k

1,174.66 rating

Confidence interval: 1,149.84 – 1,199.47

532 votes

Category
multi_turn
Evaluated configuration
hunyuan-standard-256k
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating

hunyuan-standard-256k

1,178.47 rating

Confidence interval: 1,163.08 – 1,193.86

1450 votes

Category
non_english
Evaluated configuration
hunyuan-standard-256k
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating

hunyuan-standard-256k

1,201.89 rating

Confidence interval: 1,190.33 – 1,213.45

2728 votes

Category
overall
Evaluated configuration
hunyuan-standard-256k
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-10-15 · rating

hunyuan-standard-256k

1,158.66 rating

Confidence interval: 1,132.63 – 1,184.68

444 votes

Category
russian
Evaluated configuration
hunyuan-standard-256k
Evaluation type
human preference

Run it locally

Inference · memory estimate

hunyuan-standard-256k

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Model license
Proprietary