GeekRadar / The comparison desk
COMPARE.
AI models
baidu

ERNIE-5.0-Preview (1022)

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 (1022) 1429.7 ERNIE-5.0-Preview (1022) · 95% interval 1420.9–1438.5 · 4,741 votes · 2026-11-08

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 · 2026-11-08 · rating

ERNIE-5.0-Preview (1022)

1,511.98 rating

Confidence interval: 1,482.45 – 1,541.52

390 votes

Category
chinese
Evaluated configuration
ERNIE-5.0-Preview (1022)
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-11-08 · rating

ERNIE-5.0-Preview (1022)

1,411.30 rating

Confidence interval: 1,392.81 – 1,429.78

928 votes

Category
coding
Evaluated configuration
ERNIE-5.0-Preview (1022)
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-11-08 · rating

ERNIE-5.0-Preview (1022)

1,417.96 rating

Confidence interval: 1,396.18 – 1,439.74

736 votes

Category
creative_writing
Evaluated configuration
ERNIE-5.0-Preview (1022)
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-11-08 · rating

ERNIE-5.0-Preview (1022)

1,428.68 rating

Confidence interval: 1,416.63 – 1,440.73

2200 votes

Category
english
Evaluated configuration
ERNIE-5.0-Preview (1022)
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-11-08 · rating

ERNIE-5.0-Preview (1022)

1,423.68 rating

Confidence interval: 1,411.18 – 1,436.18

3263 votes

Category
exclude_ties
Evaluated configuration
ERNIE-5.0-Preview (1022)
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-11-08 · rating

ERNIE-5.0-Preview (1022)

1,417.85 rating

Confidence interval: 1,384.56 – 1,451.14

286 votes

Category
expert
Evaluated configuration
ERNIE-5.0-Preview (1022)
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-11-08 · rating

ERNIE-5.0-Preview (1022)

1,420.26 rating

Confidence interval: 1,409.03 – 1,431.48

2584 votes

Category
hard_prompts
Evaluated configuration
ERNIE-5.0-Preview (1022)
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-11-08 · rating

ERNIE-5.0-Preview (1022)

1,411.89 rating

Confidence interval: 1,395.97 – 1,427.80

1229 votes

Category
hard_prompts_english
Evaluated configuration
ERNIE-5.0-Preview (1022)
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-11-08 · rating

ERNIE-5.0-Preview (1022)

1,416.94 rating

Confidence interval: 1,398.34 – 1,435.55

943 votes

Category
industry_business_and_management_and_financial_operations
Evaluated configuration
ERNIE-5.0-Preview (1022)
Evaluation type
human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-11-08 · rating

ERNIE-5.0-Preview (1022)

1,403.70 rating

Confidence interval: 1,384.92 – 1,422.47

934 votes

Category
industry_entertainment_and_sports_and_media
Evaluated configuration
ERNIE-5.0-Preview (1022)
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-11-08 · rating

ERNIE-5.0-Preview (1022)

1,458.83 rating

Confidence interval: 1,429.21 – 1,488.44

323 votes

Category
industry_legal_and_government
Evaluated configuration
ERNIE-5.0-Preview (1022)
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-11-08 · rating

ERNIE-5.0-Preview (1022)

1,446.38 rating

Confidence interval: 1,426.31 – 1,466.45

789 votes

Category
industry_life_and_physical_and_social_science
Evaluated configuration
ERNIE-5.0-Preview (1022)
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-11-08 · rating

ERNIE-5.0-Preview (1022)

1,430.61 rating

Confidence interval: 1,396.80 – 1,464.42

270 votes

Category
industry_mathematical
Evaluated configuration
ERNIE-5.0-Preview (1022)
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-11-08 · rating

ERNIE-5.0-Preview (1022)

1,432.03 rating

Confidence interval: 1,396.21 – 1,467.86

247 votes

Category
industry_medicine_and_healthcare
Evaluated configuration
ERNIE-5.0-Preview (1022)
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-11-08 · rating

ERNIE-5.0-Preview (1022)

1,434.45 rating

Confidence interval: 1,420.42 – 1,448.48

1631 votes

Category
industry_software_and_it_services
Evaluated configuration
ERNIE-5.0-Preview (1022)
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-11-08 · rating

ERNIE-5.0-Preview (1022)

1,409.54 rating

Confidence interval: 1,392.46 – 1,426.62

1134 votes

Category
industry_writing_and_literature_and_language
Evaluated configuration
ERNIE-5.0-Preview (1022)
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-11-08 · rating

ERNIE-5.0-Preview (1022)

1,392.74 rating

Confidence interval: 1,377.40 – 1,408.08

1353 votes

Category
instruction_following
Evaluated configuration
ERNIE-5.0-Preview (1022)
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-11-08 · rating

ERNIE-5.0-Preview (1022)

1,405.85 rating

Confidence interval: 1,389.57 – 1,422.14

1196 votes

Category
longer_query
Evaluated configuration
ERNIE-5.0-Preview (1022)
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-11-08 · rating

ERNIE-5.0-Preview (1022)

1,405.23 rating

Confidence interval: 1,371.52 – 1,438.93

273 votes

Category
math
Evaluated configuration
ERNIE-5.0-Preview (1022)
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-11-08 · rating

ERNIE-5.0-Preview (1022)

1,417.49 rating

Confidence interval: 1,396.15 – 1,438.83

713 votes

Category
multi_turn
Evaluated configuration
ERNIE-5.0-Preview (1022)
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-11-08 · rating

ERNIE-5.0-Preview (1022)

1,426.88 rating

Confidence interval: 1,415.44 – 1,438.33

2541 votes

Category
non_english
Evaluated configuration
ERNIE-5.0-Preview (1022)
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-11-08 · rating

ERNIE-5.0-Preview (1022)

1,429.69 rating

Confidence interval: 1,420.93 – 1,438.45

4741 votes

Category
overall
Evaluated configuration
ERNIE-5.0-Preview (1022)
Evaluation type
human preference
Arena text preference / polishhuman preference · 2026-11-08 · rating

ERNIE-5.0-Preview (1022)

1,482.90 rating

Confidence interval: 1,443.34 – 1,522.46

216 votes

Category
polish
Evaluated configuration
ERNIE-5.0-Preview (1022)
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-11-08 · rating

ERNIE-5.0-Preview (1022)

1,398.39 rating

Confidence interval: 1,369.17 – 1,427.61

353 votes

Category
russian
Evaluated configuration
ERNIE-5.0-Preview (1022)
Evaluation type
human preference
Arena text preference / spanishhuman preference · 2026-11-08 · rating

ERNIE-5.0-Preview (1022)

1,423.71 rating

Confidence interval: 1,378.59 – 1,468.84

165 votes

Category
spanish
Evaluated configuration
ERNIE-5.0-Preview (1022)
Evaluation type
human preference

Run it locally

Inference · memory estimate

ERNIE-5.0-Preview (1022)

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Model license
Proprietary