GeekRadar / The comparison desk
COMPARE.
AI models
tencent

Hunyuan Standard (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 Standard (2025-02-10) 1274.1 Hunyuan Standard (2025-02-10) · 95% interval 1264.4–1283.7 · 3,904 votes · 2026-11-11

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 · 2026-11-11 · rating

Hunyuan Standard (2025-02-10)

1,319.27 rating

Confidence interval: 1,288.40 – 1,350.13

340 votes

Category
chinese
Evaluated configuration
Hunyuan Standard (2025-02-10)
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-11-11 · rating

Hunyuan Standard (2025-02-10)

1,269.60 rating

Confidence interval: 1,246.07 – 1,293.13

549 votes

Category
coding
Evaluated configuration
Hunyuan Standard (2025-02-10)
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-11-11 · rating

Hunyuan Standard (2025-02-10)

1,242.03 rating

Confidence interval: 1,218.68 – 1,265.38

590 votes

Category
creative_writing
Evaluated configuration
Hunyuan Standard (2025-02-10)
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-11-11 · rating

Hunyuan Standard (2025-02-10)

1,281.46 rating

Confidence interval: 1,269.07 – 1,293.85

2312 votes

Category
english
Evaluated configuration
Hunyuan Standard (2025-02-10)
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-11-11 · rating

Hunyuan Standard (2025-02-10)

1,199.85 rating

Confidence interval: 1,184.73 – 1,214.98

2571 votes

Category
exclude_ties
Evaluated configuration
Hunyuan Standard (2025-02-10)
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-11-11 · rating

Hunyuan Standard (2025-02-10)

1,247.43 rating

Confidence interval: 1,208.73 – 1,286.13

207 votes

Category
expert
Evaluated configuration
Hunyuan Standard (2025-02-10)
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-11-11 · rating

Hunyuan Standard (2025-02-10)

1,264.26 rating

Confidence interval: 1,245.69 – 1,282.82

873 votes

Category
hard_prompts
Evaluated configuration
Hunyuan Standard (2025-02-10)
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-11-11 · rating

Hunyuan Standard (2025-02-10)

1,273.85 rating

Confidence interval: 1,250.69 – 1,297.00

587 votes

Category
hard_prompts_english
Evaluated configuration
Hunyuan Standard (2025-02-10)
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-11-11 · rating

Hunyuan Standard (2025-02-10)

1,254.77 rating

Confidence interval: 1,226.03 – 1,283.51

376 votes

Category
industry_business_and_management_and_financial_operations
Evaluated configuration
Hunyuan Standard (2025-02-10)
Evaluation type
human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-11-11 · rating

Hunyuan Standard (2025-02-10)

1,222.30 rating

Confidence interval: 1,200.61 – 1,243.98

675 votes

Category
industry_entertainment_and_sports_and_media
Evaluated configuration
Hunyuan Standard (2025-02-10)
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-11-11 · rating

Hunyuan Standard (2025-02-10)

1,289.75 rating

Confidence interval: 1,255.85 – 1,323.65

288 votes

Category
industry_legal_and_government
Evaluated configuration
Hunyuan Standard (2025-02-10)
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-11-11 · rating

Hunyuan Standard (2025-02-10)

1,284.48 rating

Confidence interval: 1,262.95 – 1,306.01

696 votes

Category
industry_life_and_physical_and_social_science
Evaluated configuration
Hunyuan Standard (2025-02-10)
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-11-11 · rating

Hunyuan Standard (2025-02-10)

1,288.39 rating

Confidence interval: 1,263.01 – 1,313.78

441 votes

Category
industry_mathematical
Evaluated configuration
Hunyuan Standard (2025-02-10)
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-11-11 · rating

Hunyuan Standard (2025-02-10)

1,309.45 rating

Confidence interval: 1,273.02 – 1,345.88

247 votes

Category
industry_medicine_and_healthcare
Evaluated configuration
Hunyuan Standard (2025-02-10)
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-11-11 · rating

Hunyuan Standard (2025-02-10)

1,284.62 rating

Confidence interval: 1,265.53 – 1,303.70

880 votes

Category
industry_software_and_it_services
Evaluated configuration
Hunyuan Standard (2025-02-10)
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-11-11 · rating

Hunyuan Standard (2025-02-10)

1,257.03 rating

Confidence interval: 1,238.96 – 1,275.10

937 votes

Category
industry_writing_and_literature_and_language
Evaluated configuration
Hunyuan Standard (2025-02-10)
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-11-11 · rating

Hunyuan Standard (2025-02-10)

1,244.77 rating

Confidence interval: 1,229.64 – 1,259.90

1329 votes

Category
instruction_following
Evaluated configuration
Hunyuan Standard (2025-02-10)
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-11-11 · rating

Hunyuan Standard (2025-02-10)

1,300.66 rating

Confidence interval: 1,274.05 – 1,327.28

432 votes

Category
longer_query
Evaluated configuration
Hunyuan Standard (2025-02-10)
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-11-11 · rating

Hunyuan Standard (2025-02-10)

1,274.19 rating

Confidence interval: 1,250.37 – 1,298.00

499 votes

Category
math
Evaluated configuration
Hunyuan Standard (2025-02-10)
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-11-11 · rating

Hunyuan Standard (2025-02-10)

1,274.75 rating

Confidence interval: 1,250.99 – 1,298.51

570 votes

Category
multi_turn
Evaluated configuration
Hunyuan Standard (2025-02-10)
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-11-11 · rating

Hunyuan Standard (2025-02-10)

1,261.48 rating

Confidence interval: 1,247.37 – 1,275.60

1592 votes

Category
non_english
Evaluated configuration
Hunyuan Standard (2025-02-10)
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-11-11 · rating

Hunyuan Standard (2025-02-10)

1,274.05 rating

Confidence interval: 1,264.41 – 1,283.69

3904 votes

Category
overall
Evaluated configuration
Hunyuan Standard (2025-02-10)
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-11-11 · rating

Hunyuan Standard (2025-02-10)

1,258.18 rating

Confidence interval: 1,231.36 – 1,285.01

379 votes

Category
russian
Evaluated configuration
Hunyuan Standard (2025-02-10)
Evaluation type
human preference

Run it locally

Inference · memory estimate

Hunyuan Standard (2025-02-10)

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Model license
Proprietary