GeekRadar / The comparison desk
COMPARE.
AI models
tencent

hunyuan-large-2025-02-10

Model evaluation

Capability & preference

Human preference · Arena

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

hunyuan-large-2025-02-10 1287.9 hunyuan-large-2025-02-10 · 95% interval 1278.2–1297.6 · 3,738 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-large-2025-02-10

1,345.86 rating

Confidence interval: 1,313.32 – 1,378.40

295 votes

Category
chinese
Evaluated configuration
hunyuan-large-2025-02-10
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating

hunyuan-large-2025-02-10

1,306.56 rating

Confidence interval: 1,282.26 – 1,330.85

519 votes

Category
coding
Evaluated configuration
hunyuan-large-2025-02-10
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating

hunyuan-large-2025-02-10

1,264.19 rating

Confidence interval: 1,240.60 – 1,287.77

568 votes

Category
creative_writing
Evaluated configuration
hunyuan-large-2025-02-10
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating

hunyuan-large-2025-02-10

1,305.00 rating

Confidence interval: 1,292.75 – 1,317.25

2255 votes

Category
english
Evaluated configuration
hunyuan-large-2025-02-10
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating

hunyuan-large-2025-02-10

1,216.92 rating

Confidence interval: 1,201.90 – 1,231.94

2472 votes

Category
exclude_ties
Evaluated configuration
hunyuan-large-2025-02-10
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-15 · rating

hunyuan-large-2025-02-10

1,275.37 rating

Confidence interval: 1,239.56 – 1,311.18

228 votes

Category
expert
Evaluated configuration
hunyuan-large-2025-02-10
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating

hunyuan-large-2025-02-10

1,286.17 rating

Confidence interval: 1,267.55 – 1,304.79

889 votes

Category
hard_prompts
Evaluated configuration
hunyuan-large-2025-02-10
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating

hunyuan-large-2025-02-10

1,294.25 rating

Confidence interval: 1,271.84 – 1,316.66

601 votes

Category
hard_prompts_english
Evaluated configuration
hunyuan-large-2025-02-10
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating

hunyuan-large-2025-02-10

1,241.25 rating

Confidence interval: 1,210.36 – 1,272.13

357 votes

Category
industry_business_and_management_and_financial_operations
Evaluated configuration
hunyuan-large-2025-02-10
Evaluation type
human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating

hunyuan-large-2025-02-10

1,261.99 rating

Confidence interval: 1,240.08 – 1,283.90

646 votes

Category
industry_entertainment_and_sports_and_media
Evaluated configuration
hunyuan-large-2025-02-10
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating

hunyuan-large-2025-02-10

1,280.36 rating

Confidence interval: 1,244.47 – 1,316.25

252 votes

Category
industry_legal_and_government
Evaluated configuration
hunyuan-large-2025-02-10
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating

hunyuan-large-2025-02-10

1,291.24 rating

Confidence interval: 1,270.39 – 1,312.09

707 votes

Category
industry_life_and_physical_and_social_science
Evaluated configuration
hunyuan-large-2025-02-10
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating

hunyuan-large-2025-02-10

1,304.35 rating

Confidence interval: 1,278.32 – 1,330.37

431 votes

Category
industry_mathematical
Evaluated configuration
hunyuan-large-2025-02-10
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating

hunyuan-large-2025-02-10

1,340.06 rating

Confidence interval: 1,301.96 – 1,378.17

212 votes

Category
industry_medicine_and_healthcare
Evaluated configuration
hunyuan-large-2025-02-10
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating

hunyuan-large-2025-02-10

1,306.16 rating

Confidence interval: 1,286.79 – 1,325.54

828 votes

Category
industry_software_and_it_services
Evaluated configuration
hunyuan-large-2025-02-10
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating

hunyuan-large-2025-02-10

1,270.97 rating

Confidence interval: 1,252.26 – 1,289.67

890 votes

Category
industry_writing_and_literature_and_language
Evaluated configuration
hunyuan-large-2025-02-10
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating

hunyuan-large-2025-02-10

1,277.01 rating

Confidence interval: 1,261.54 – 1,292.47

1300 votes

Category
instruction_following
Evaluated configuration
hunyuan-large-2025-02-10
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating

hunyuan-large-2025-02-10

1,341.25 rating

Confidence interval: 1,313.47 – 1,369.04

371 votes

Category
longer_query
Evaluated configuration
hunyuan-large-2025-02-10
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating

hunyuan-large-2025-02-10

1,280.70 rating

Confidence interval: 1,256.79 – 1,304.62

497 votes

Category
math
Evaluated configuration
hunyuan-large-2025-02-10
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating

hunyuan-large-2025-02-10

1,284.42 rating

Confidence interval: 1,259.28 – 1,309.56

510 votes

Category
multi_turn
Evaluated configuration
hunyuan-large-2025-02-10
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating

hunyuan-large-2025-02-10

1,265.23 rating

Confidence interval: 1,250.34 – 1,280.12

1483 votes

Category
non_english
Evaluated configuration
hunyuan-large-2025-02-10
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating

hunyuan-large-2025-02-10

1,287.92 rating

Confidence interval: 1,278.19 – 1,297.65

3738 votes

Category
overall
Evaluated configuration
hunyuan-large-2025-02-10
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-10-15 · rating

hunyuan-large-2025-02-10

1,265.91 rating

Confidence interval: 1,237.45 – 1,294.37

374 votes

Category
russian
Evaluated configuration
hunyuan-large-2025-02-10
Evaluation type
human preference

Run it locally

Inference · memory estimate

hunyuan-large-2025-02-10

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Model license
Proprietary