GeekRadar / The comparison desk

COMPARE.

AI models

baidu

ERNIE 5.0 (0110)

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 (0110) 1444.5 ERNIE 5.0 (0110) · 95% interval 1440.7–1448.4 · 36,475 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 (0110)

1,492.70 rating

Confidence interval: 1,480.70 – 1,504.69

2541 votes

Oct 28, 2026

Category: chinese
Evaluated configuration: ERNIE 5.0 (0110)
Evaluation type: human preference

Arena text preference / codinghuman preference · 2026-10-28 · rating

ERNIE 5.0 (0110)

1,454.69 rating

Confidence interval: 1,448.15 – 1,461.24

8954 votes

Oct 28, 2026

Category: coding
Evaluated configuration: ERNIE 5.0 (0110)
Evaluation type: human preference

Arena text preference / creative_writinghuman preference · 2026-10-28 · rating

ERNIE 5.0 (0110)

1,426.24 rating

Confidence interval: 1,418.12 – 1,434.35

5764 votes

Oct 28, 2026

Category: creative_writing
Evaluated configuration: ERNIE 5.0 (0110)
Evaluation type: human preference

Arena text preference / englishhuman preference · 2026-10-28 · rating

ERNIE 5.0 (0110)

1,448.24 rating

Confidence interval: 1,442.90 – 1,453.57

15126 votes

Oct 28, 2026

Category: english
Evaluated configuration: ERNIE 5.0 (0110)
Evaluation type: human preference

Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating

ERNIE 5.0 (0110)

1,443.17 rating

Confidence interval: 1,437.89 – 1,448.46

26016 votes

Oct 28, 2026

Category: exclude_ties
Evaluated configuration: ERNIE 5.0 (0110)
Evaluation type: human preference

Arena text preference / experthuman preference · 2026-10-28 · rating

ERNIE 5.0 (0110)

1,426.98 rating

Confidence interval: 1,416.14 – 1,437.81

2953 votes

Oct 28, 2026

Category: expert
Evaluated configuration: ERNIE 5.0 (0110)
Evaluation type: human preference

Arena text preference / frenchhuman preference · 2026-10-28 · rating

ERNIE 5.0 (0110)

1,459.39 rating

Confidence interval: 1,440.73 – 1,478.06

1093 votes

Oct 28, 2026

Category: french
Evaluated configuration: ERNIE 5.0 (0110)
Evaluation type: human preference

Arena text preference / germanhuman preference · 2026-10-28 · rating

ERNIE 5.0 (0110)

1,436.52 rating

Confidence interval: 1,413.52 – 1,459.53

661 votes

Oct 28, 2026

Category: german
Evaluated configuration: ERNIE 5.0 (0110)
Evaluation type: human preference

Arena text preference / hard_promptshuman preference · 2026-10-28 · rating

ERNIE 5.0 (0110)

1,445.14 rating

Confidence interval: 1,440.40 – 1,449.88

21822 votes

Oct 28, 2026

Category: hard_prompts
Evaluated configuration: ERNIE 5.0 (0110)
Evaluation type: human preference

Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating

ERNIE 5.0 (0110)

1,447.59 rating

Confidence interval: 1,441.06 – 1,454.13

9156 votes

Oct 28, 2026

Category: hard_prompts_english
Evaluated configuration: ERNIE 5.0 (0110)
Evaluation type: human preference

Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating

ERNIE 5.0 (0110)

1,428.55 rating

Confidence interval: 1,421.29 – 1,435.81

7038 votes

Oct 28, 2026

Category: industry_business_and_management_and_financial_operations
Evaluated configuration: ERNIE 5.0 (0110)
Evaluation type: human preference

Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating

ERNIE 5.0 (0110)

1,410.98 rating

Confidence interval: 1,403.55 – 1,418.41

6914 votes

Oct 28, 2026

Category: industry_entertainment_and_sports_and_media
Evaluated configuration: ERNIE 5.0 (0110)
Evaluation type: human preference

Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-28 · rating

ERNIE 5.0 (0110)

1,435.29 rating

Confidence interval: 1,423.72 – 1,446.87

2675 votes

Oct 28, 2026

Category: industry_legal_and_government
Evaluated configuration: ERNIE 5.0 (0110)
Evaluation type: human preference

Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating

ERNIE 5.0 (0110)

1,450.51 rating

Confidence interval: 1,442.80 – 1,458.23

6110 votes

Oct 28, 2026

Category: industry_life_and_physical_and_social_science
Evaluated configuration: ERNIE 5.0 (0110)
Evaluation type: human preference

Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating

ERNIE 5.0 (0110)

1,431.80 rating

Confidence interval: 1,418.25 – 1,445.34

1871 votes

Oct 28, 2026

Category: industry_mathematical
Evaluated configuration: ERNIE 5.0 (0110)
Evaluation type: human preference

Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating

ERNIE 5.0 (0110)

1,459.59 rating

Confidence interval: 1,447.68 – 1,471.49

2492 votes

Oct 28, 2026

Category: industry_medicine_and_healthcare
Evaluated configuration: ERNIE 5.0 (0110)
Evaluation type: human preference

Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating

ERNIE 5.0 (0110)

1,462.12 rating

Confidence interval: 1,456.57 – 1,467.68

13549 votes

Oct 28, 2026

Category: industry_software_and_it_services
Evaluated configuration: ERNIE 5.0 (0110)
Evaluation type: human preference

Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating

ERNIE 5.0 (0110)

1,421.36 rating

Confidence interval: 1,414.59 – 1,428.13

8363 votes

Oct 28, 2026

Category: industry_writing_and_literature_and_language
Evaluated configuration: ERNIE 5.0 (0110)
Evaluation type: human preference

Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating

ERNIE 5.0 (0110)

1,413.06 rating

Confidence interval: 1,407.03 – 1,419.09

11103 votes

Oct 28, 2026

Category: instruction_following
Evaluated configuration: ERNIE 5.0 (0110)
Evaluation type: human preference

Arena text preference / japanesehuman preference · 2026-10-28 · rating

ERNIE 5.0 (0110)

1,381.90 rating

Confidence interval: 1,350.65 – 1,413.15

385 votes

Oct 28, 2026

Category: japanese
Evaluated configuration: ERNIE 5.0 (0110)
Evaluation type: human preference

Arena text preference / koreanhuman preference · 2026-10-28 · rating

ERNIE 5.0 (0110)

1,407.43 rating

Confidence interval: 1,384.03 – 1,430.83

648 votes

Oct 28, 2026

Category: korean
Evaluated configuration: ERNIE 5.0 (0110)
Evaluation type: human preference

Arena text preference / longer_queryhuman preference · 2026-10-28 · rating

ERNIE 5.0 (0110)

1,421.67 rating

Confidence interval: 1,415.68 – 1,427.65

11920 votes

Oct 28, 2026

Category: longer_query
Evaluated configuration: ERNIE 5.0 (0110)
Evaluation type: human preference

Arena text preference / mathhuman preference · 2026-10-28 · rating

ERNIE 5.0 (0110)

1,436.04 rating

Confidence interval: 1,423.76 – 1,448.33

2256 votes

Oct 28, 2026

Category: math
Evaluated configuration: ERNIE 5.0 (0110)
Evaluation type: human preference

Arena text preference / multi_turnhuman preference · 2026-10-28 · rating

ERNIE 5.0 (0110)

1,433.28 rating

Confidence interval: 1,425.36 – 1,441.20

5902 votes

Oct 28, 2026

Category: multi_turn
Evaluated configuration: ERNIE 5.0 (0110)
Evaluation type: human preference

Arena text preference / non_englishhuman preference · 2026-10-28 · rating

ERNIE 5.0 (0110)

1,435.43 rating

Confidence interval: 1,430.73 – 1,440.12

21349 votes

Oct 28, 2026

Category: non_english
Evaluated configuration: ERNIE 5.0 (0110)
Evaluation type: human preference

Arena text preference / overallhuman preference · 2026-10-28 · rating

ERNIE 5.0 (0110)

1,444.52 rating

Confidence interval: 1,440.66 – 1,448.38

36475 votes

Oct 28, 2026

Category: overall
Evaluated configuration: ERNIE 5.0 (0110)
Evaluation type: human preference

Arena text preference / polishhuman preference · 2026-10-28 · rating

ERNIE 5.0 (0110)

1,467.15 rating

Confidence interval: 1,447.80 – 1,486.49

928 votes

Oct 28, 2026

Category: polish
Evaluated configuration: ERNIE 5.0 (0110)
Evaluation type: human preference

Arena text preference / russianhuman preference · 2026-10-28 · rating

ERNIE 5.0 (0110)

1,445.31 rating

Confidence interval: 1,436.62 – 1,454.00

4631 votes

Oct 28, 2026

Category: russian
Evaluated configuration: ERNIE 5.0 (0110)
Evaluation type: human preference

Arena text preference / spanishhuman preference · 2026-10-28 · rating

ERNIE 5.0 (0110)

1,447.23 rating

Confidence interval: 1,431.21 – 1,463.25

1390 votes

Oct 28, 2026

Category: spanish
Evaluated configuration: ERNIE 5.0 (0110)
Evaluation type: human preference

Run it locally

Inference · memory estimate

ERNIE 5.0 (0110)

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Model license: Proprietary