GeekRadar / The comparison desk
COMPARE.
AI models
baidu

ERNIE 5.1

Model evaluation

Capability & preference

Human preference · Arena

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

ERNIE 5.1 1467.8 ERNIE 5.1 · 95% interval 1463.3–1472.3 · 39,469 votes · 2026-10-28

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 · 2026-10-28 · rating

ERNIE 5.1

1,506.87 rating

Confidence interval: 1,493.47 – 1,520.27

2098 votes

Category
chinese
Evaluated configuration
ERNIE 5.1
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating

ERNIE 5.1

1,487.61 rating

Confidence interval: 1,480.73 – 1,494.50

10923 votes

Category
coding
Evaluated configuration
ERNIE 5.1
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating

ERNIE 5.1

1,440.77 rating

Confidence interval: 1,432.47 – 1,449.06

6445 votes

Category
creative_writing
Evaluated configuration
ERNIE 5.1
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating

ERNIE 5.1

1,477.52 rating

Confidence interval: 1,471.78 – 1,483.26

17985 votes

Category
english
Evaluated configuration
ERNIE 5.1
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating

ERNIE 5.1

1,471.78 rating

Confidence interval: 1,465.96 – 1,477.59

29981 votes

Category
exclude_ties
Evaluated configuration
ERNIE 5.1
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-28 · rating

ERNIE 5.1

1,491.04 rating

Confidence interval: 1,480.84 – 1,501.24

3728 votes

Category
expert
Evaluated configuration
ERNIE 5.1
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-10-28 · rating

ERNIE 5.1

1,486.02 rating

Confidence interval: 1,469.13 – 1,502.91

1501 votes

Category
french
Evaluated configuration
ERNIE 5.1
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-28 · rating

ERNIE 5.1

1,469.53 rating

Confidence interval: 1,447.70 – 1,491.36

750 votes

Category
german
Evaluated configuration
ERNIE 5.1
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating

ERNIE 5.1

1,480.64 rating

Confidence interval: 1,475.37 – 1,485.91

25670 votes

Category
hard_prompts
Evaluated configuration
ERNIE 5.1
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating

ERNIE 5.1

1,484.77 rating

Confidence interval: 1,478.17 – 1,491.37

12427 votes

Category
hard_prompts_english
Evaluated configuration
ERNIE 5.1
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating

ERNIE 5.1

1,473.01 rating

Confidence interval: 1,465.38 – 1,480.63

7814 votes

Category
industry_business_and_management_and_financial_operations
Evaluated configuration
ERNIE 5.1
Evaluation type
human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating

ERNIE 5.1

1,435.56 rating

Confidence interval: 1,428.01 – 1,443.10

8466 votes

Category
industry_entertainment_and_sports_and_media
Evaluated configuration
ERNIE 5.1
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-28 · rating

ERNIE 5.1

1,468.15 rating

Confidence interval: 1,456.99 – 1,479.32

3130 votes

Category
industry_legal_and_government
Evaluated configuration
ERNIE 5.1
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating

ERNIE 5.1

1,483.47 rating

Confidence interval: 1,475.38 – 1,491.56

6388 votes

Category
industry_life_and_physical_and_social_science
Evaluated configuration
ERNIE 5.1
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating

ERNIE 5.1

1,491.46 rating

Confidence interval: 1,477.98 – 1,504.94

2047 votes

Category
industry_mathematical
Evaluated configuration
ERNIE 5.1
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating

ERNIE 5.1

1,487.20 rating

Confidence interval: 1,475.61 – 1,498.80

2908 votes

Category
industry_medicine_and_healthcare
Evaluated configuration
ERNIE 5.1
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating

ERNIE 5.1

1,491.94 rating

Confidence interval: 1,485.86 – 1,498.01

15688 votes

Category
industry_software_and_it_services
Evaluated configuration
ERNIE 5.1
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating

ERNIE 5.1

1,449.05 rating

Confidence interval: 1,441.86 – 1,456.23

9634 votes

Category
industry_writing_and_literature_and_language
Evaluated configuration
ERNIE 5.1
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating

ERNIE 5.1

1,460.33 rating

Confidence interval: 1,453.80 – 1,466.85

12664 votes

Category
instruction_following
Evaluated configuration
ERNIE 5.1
Evaluation type
human preference
Arena text preference / japanesehuman preference · 2026-10-28 · rating

ERNIE 5.1

1,421.31 rating

Confidence interval: 1,394.57 – 1,448.05

515 votes

Category
japanese
Evaluated configuration
ERNIE 5.1
Evaluation type
human preference
Arena text preference / koreanhuman preference · 2026-10-28 · rating

ERNIE 5.1

1,425.96 rating

Confidence interval: 1,401.72 – 1,450.20

657 votes

Category
korean
Evaluated configuration
ERNIE 5.1
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-10-28 · rating

ERNIE 5.1

1,461.74 rating

Confidence interval: 1,455.55 – 1,467.92

16715 votes

Category
longer_query
Evaluated configuration
ERNIE 5.1
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-10-28 · rating

ERNIE 5.1

1,481.59 rating

Confidence interval: 1,468.24 – 1,494.93

1985 votes

Category
math
Evaluated configuration
ERNIE 5.1
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-10-28 · rating

ERNIE 5.1

1,470.34 rating

Confidence interval: 1,462.20 – 1,478.49

6809 votes

Category
multi_turn
Evaluated configuration
ERNIE 5.1
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-10-28 · rating

ERNIE 5.1

1,454.21 rating

Confidence interval: 1,448.76 – 1,459.67

21484 votes

Category
non_english
Evaluated configuration
ERNIE 5.1
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-10-28 · rating

ERNIE 5.1

1,467.77 rating

Confidence interval: 1,463.26 – 1,472.28

39469 votes

Category
overall
Evaluated configuration
ERNIE 5.1
Evaluation type
human preference
Arena text preference / polishhuman preference · 2026-10-28 · rating

ERNIE 5.1

1,467.89 rating

Confidence interval: 1,447.33 – 1,488.46

774 votes

Category
polish
Evaluated configuration
ERNIE 5.1
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-10-28 · rating

ERNIE 5.1

1,459.13 rating

Confidence interval: 1,449.66 – 1,468.59

4341 votes

Category
russian
Evaluated configuration
ERNIE 5.1
Evaluation type
human preference
Arena text preference / spanishhuman preference · 2026-10-28 · rating

ERNIE 5.1

1,473.22 rating

Confidence interval: 1,455.47 – 1,490.96

1296 votes

Category
spanish
Evaluated configuration
ERNIE 5.1
Evaluation type
human preference

Run it locally

Inference · memory estimate

ERNIE 5.1

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Model license
Proprietary