GeekRadar / The comparison desk
COMPARE.
AI models
baidu

ERNIE-5.0-Preview (1203)

Model evaluation

Capability & preference

Human preference · Arena

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

ERNIE-5.0-Preview (1203) 1442.3 ERNIE-5.0-Preview (1203) · 95% interval 1435.8–1448.8 · 9,802 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-5.0-Preview (1203)

1,500.65 rating

Confidence interval: 1,480.00 – 1,521.29

830 votes

Category
chinese
Evaluated configuration
ERNIE-5.0-Preview (1203)
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating

ERNIE-5.0-Preview (1203)

1,425.53 rating

Confidence interval: 1,412.42 – 1,438.64

1990 votes

Category
coding
Evaluated configuration
ERNIE-5.0-Preview (1203)
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating

ERNIE-5.0-Preview (1203)

1,422.06 rating

Confidence interval: 1,407.08 – 1,437.04

1579 votes

Category
creative_writing
Evaluated configuration
ERNIE-5.0-Preview (1203)
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating

ERNIE-5.0-Preview (1203)

1,442.86 rating

Confidence interval: 1,433.59 – 1,452.14

4094 votes

Category
english
Evaluated configuration
ERNIE-5.0-Preview (1203)
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating

ERNIE-5.0-Preview (1203)

1,440.00 rating

Confidence interval: 1,430.97 – 1,449.03

6941 votes

Category
exclude_ties
Evaluated configuration
ERNIE-5.0-Preview (1203)
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-28 · rating

ERNIE-5.0-Preview (1203)

1,422.31 rating

Confidence interval: 1,401.00 – 1,443.62

727 votes

Category
expert
Evaluated configuration
ERNIE-5.0-Preview (1203)
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-10-28 · rating

ERNIE-5.0-Preview (1203)

1,467.20 rating

Confidence interval: 1,429.75 – 1,504.64

254 votes

Category
french
Evaluated configuration
ERNIE-5.0-Preview (1203)
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-28 · rating

ERNIE-5.0-Preview (1203)

1,460.36 rating

Confidence interval: 1,419.34 – 1,501.38

222 votes

Category
german
Evaluated configuration
ERNIE-5.0-Preview (1203)
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating

ERNIE-5.0-Preview (1203)

1,438.00 rating

Confidence interval: 1,429.65 – 1,446.34

5293 votes

Category
hard_prompts
Evaluated configuration
ERNIE-5.0-Preview (1203)
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating

ERNIE-5.0-Preview (1203)

1,436.67 rating

Confidence interval: 1,424.15 – 1,449.19

2166 votes

Category
hard_prompts_english
Evaluated configuration
ERNIE-5.0-Preview (1203)
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating

ERNIE-5.0-Preview (1203)

1,423.38 rating

Confidence interval: 1,409.95 – 1,436.82

1892 votes

Category
industry_business_and_management_and_financial_operations
Evaluated configuration
ERNIE-5.0-Preview (1203)
Evaluation type
human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating

ERNIE-5.0-Preview (1203)

1,405.96 rating

Confidence interval: 1,392.87 – 1,419.06

1921 votes

Category
industry_entertainment_and_sports_and_media
Evaluated configuration
ERNIE-5.0-Preview (1203)
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-28 · rating

ERNIE-5.0-Preview (1203)

1,447.79 rating

Confidence interval: 1,427.21 – 1,468.37

773 votes

Category
industry_legal_and_government
Evaluated configuration
ERNIE-5.0-Preview (1203)
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating

ERNIE-5.0-Preview (1203)

1,468.07 rating

Confidence interval: 1,453.63 – 1,482.51

1638 votes

Category
industry_life_and_physical_and_social_science
Evaluated configuration
ERNIE-5.0-Preview (1203)
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating

ERNIE-5.0-Preview (1203)

1,410.54 rating

Confidence interval: 1,385.15 – 1,435.92

520 votes

Category
industry_mathematical
Evaluated configuration
ERNIE-5.0-Preview (1203)
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating

ERNIE-5.0-Preview (1203)

1,471.44 rating

Confidence interval: 1,449.08 – 1,493.80

693 votes

Category
industry_medicine_and_healthcare
Evaluated configuration
ERNIE-5.0-Preview (1203)
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating

ERNIE-5.0-Preview (1203)

1,447.30 rating

Confidence interval: 1,437.06 – 1,457.54

3325 votes

Category
industry_software_and_it_services
Evaluated configuration
ERNIE-5.0-Preview (1203)
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating

ERNIE-5.0-Preview (1203)

1,414.15 rating

Confidence interval: 1,401.78 – 1,426.53

2215 votes

Category
industry_writing_and_literature_and_language
Evaluated configuration
ERNIE-5.0-Preview (1203)
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating

ERNIE-5.0-Preview (1203)

1,401.29 rating

Confidence interval: 1,390.10 – 1,412.47

2680 votes

Category
instruction_following
Evaluated configuration
ERNIE-5.0-Preview (1203)
Evaluation type
human preference
Arena text preference / koreanhuman preference · 2026-10-28 · rating

ERNIE-5.0-Preview (1203)

1,371.86 rating

Confidence interval: 1,327.28 – 1,416.43

158 votes

Category
korean
Evaluated configuration
ERNIE-5.0-Preview (1203)
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-10-28 · rating

ERNIE-5.0-Preview (1203)

1,409.17 rating

Confidence interval: 1,397.67 – 1,420.66

2567 votes

Category
longer_query
Evaluated configuration
ERNIE-5.0-Preview (1203)
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-10-28 · rating

ERNIE-5.0-Preview (1203)

1,410.13 rating

Confidence interval: 1,387.56 – 1,432.69

629 votes

Category
math
Evaluated configuration
ERNIE-5.0-Preview (1203)
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-10-28 · rating

ERNIE-5.0-Preview (1203)

1,408.64 rating

Confidence interval: 1,393.64 – 1,423.64

1548 votes

Category
multi_turn
Evaluated configuration
ERNIE-5.0-Preview (1203)
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-10-28 · rating

ERNIE-5.0-Preview (1203)

1,435.02 rating

Confidence interval: 1,426.90 – 1,443.14

5708 votes

Category
non_english
Evaluated configuration
ERNIE-5.0-Preview (1203)
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-10-28 · rating

ERNIE-5.0-Preview (1203)

1,442.29 rating

Confidence interval: 1,435.83 – 1,448.75

9802 votes

Category
overall
Evaluated configuration
ERNIE-5.0-Preview (1203)
Evaluation type
human preference
Arena text preference / polishhuman preference · 2026-10-28 · rating

ERNIE-5.0-Preview (1203)

1,482.72 rating

Confidence interval: 1,452.09 – 1,513.36

355 votes

Category
polish
Evaluated configuration
ERNIE-5.0-Preview (1203)
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-10-28 · rating

ERNIE-5.0-Preview (1203)

1,436.32 rating

Confidence interval: 1,420.00 – 1,452.64

1186 votes

Category
russian
Evaluated configuration
ERNIE-5.0-Preview (1203)
Evaluation type
human preference
Arena text preference / spanishhuman preference · 2026-10-28 · rating

ERNIE-5.0-Preview (1203)

1,472.63 rating

Confidence interval: 1,435.84 – 1,509.42

239 votes

Category
spanish
Evaluated configuration
ERNIE-5.0-Preview (1203)
Evaluation type
human preference

Run it locally

Inference · memory estimate

ERNIE-5.0-Preview (1203)

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Model license
Proprietary