GeekRadar / The comparison desk

COMPARE.

AI models

Not reported

Yi 1.5 34B Chat

Model evaluation

Capability & preference

Human preference · Arena

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

Yi 1.5 34B Chat 1172.9 Yi 1.5 34B Chat · 95% interval 1167.9–1177.9 · 24,146 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

Yi 1.5 34B Chat

1,212.95 rating

Confidence interval: 1,200.12 – 1,225.78

2868 votes

Oct 28, 2026

Category: chinese
Evaluated configuration: Yi 1.5 34B Chat
Evaluation type: human preference

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

Yi 1.5 34B Chat

1,168.99 rating

Confidence interval: 1,158.59 – 1,179.39

3841 votes

Oct 28, 2026

Category: coding
Evaluated configuration: Yi 1.5 34B Chat
Evaluation type: human preference

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

Yi 1.5 34B Chat

1,134.84 rating

Confidence interval: 1,123.80 – 1,145.89

3602 votes

Oct 28, 2026

Category: creative_writing
Evaluated configuration: Yi 1.5 34B Chat
Evaluation type: human preference

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

Yi 1.5 34B Chat

1,214.74 rating

Confidence interval: 1,207.93 – 1,221.55

12503 votes

Oct 28, 2026

Category: english
Evaluated configuration: Yi 1.5 34B Chat
Evaluation type: human preference

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

Yi 1.5 34B Chat

1,042.65 rating

Confidence interval: 1,034.48 – 1,050.82

15321 votes

Oct 28, 2026

Category: exclude_ties
Evaluated configuration: Yi 1.5 34B Chat
Evaluation type: human preference

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

Yi 1.5 34B Chat

1,143.78 rating

Confidence interval: 1,125.37 – 1,162.19

1049 votes

Oct 28, 2026

Category: expert
Evaluated configuration: Yi 1.5 34B Chat
Evaluation type: human preference

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

Yi 1.5 34B Chat

1,156.74 rating

Confidence interval: 1,124.51 – 1,188.98

399 votes

Oct 28, 2026

Category: french
Evaluated configuration: Yi 1.5 34B Chat
Evaluation type: human preference

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

Yi 1.5 34B Chat

1,110.84 rating

Confidence interval: 1,090.02 – 1,131.67

871 votes

Oct 28, 2026

Category: german
Evaluated configuration: Yi 1.5 34B Chat
Evaluation type: human preference

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

Yi 1.5 34B Chat

1,159.69 rating

Confidence interval: 1,151.42 – 1,167.95

6679 votes

Oct 28, 2026

Category: hard_prompts
Evaluated configuration: Yi 1.5 34B Chat
Evaluation type: human preference

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

Yi 1.5 34B Chat

1,179.56 rating

Confidence interval: 1,169.52 – 1,189.60

3931 votes

Oct 28, 2026

Category: hard_prompts_english
Evaluated configuration: Yi 1.5 34B Chat
Evaluation type: human preference

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

Yi 1.5 34B Chat

1,134.69 rating

Confidence interval: 1,122.46 – 1,146.91

2763 votes

Oct 28, 2026

Category: industry_business_and_management_and_financial_operations
Evaluated configuration: Yi 1.5 34B Chat
Evaluation type: human preference

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

Yi 1.5 34B Chat

1,120.59 rating

Confidence interval: 1,110.02 – 1,131.17

3893 votes

Oct 28, 2026

Category: industry_entertainment_and_sports_and_media
Evaluated configuration: Yi 1.5 34B Chat
Evaluation type: human preference

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

Yi 1.5 34B Chat

1,196.39 rating

Confidence interval: 1,179.94 – 1,212.83

1510 votes

Oct 28, 2026

Category: industry_legal_and_government
Evaluated configuration: Yi 1.5 34B Chat
Evaluation type: human preference

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

Yi 1.5 34B Chat

1,173.10 rating

Confidence interval: 1,162.31 – 1,183.88

4292 votes

Oct 28, 2026

Category: industry_life_and_physical_and_social_science
Evaluated configuration: Yi 1.5 34B Chat
Evaluation type: human preference

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

Yi 1.5 34B Chat

1,185.37 rating

Confidence interval: 1,173.69 – 1,197.05

2568 votes

Oct 28, 2026

Category: industry_mathematical
Evaluated configuration: Yi 1.5 34B Chat
Evaluation type: human preference

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

Yi 1.5 34B Chat

1,159.28 rating

Confidence interval: 1,141.71 – 1,176.85

1330 votes

Oct 28, 2026

Category: industry_medicine_and_healthcare
Evaluated configuration: Yi 1.5 34B Chat
Evaluation type: human preference

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

Yi 1.5 34B Chat

1,171.84 rating

Confidence interval: 1,163.16 – 1,180.53

6462 votes

Oct 28, 2026

Category: industry_software_and_it_services
Evaluated configuration: Yi 1.5 34B Chat
Evaluation type: human preference

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

Yi 1.5 34B Chat

1,144.06 rating

Confidence interval: 1,135.25 – 1,152.86

6540 votes

Oct 28, 2026

Category: industry_writing_and_literature_and_language
Evaluated configuration: Yi 1.5 34B Chat
Evaluation type: human preference

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

Yi 1.5 34B Chat

1,139.06 rating

Confidence interval: 1,131.43 – 1,146.69

8996 votes

Oct 28, 2026

Category: instruction_following
Evaluated configuration: Yi 1.5 34B Chat
Evaluation type: human preference

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

Yi 1.5 34B Chat

1,021.47 rating

Confidence interval: 993.36 – 1,049.58

506 votes

Oct 28, 2026

Category: japanese
Evaluated configuration: Yi 1.5 34B Chat
Evaluation type: human preference

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

Yi 1.5 34B Chat

1,005.23 rating

Confidence interval: 980.27 – 1,030.19

804 votes

Oct 28, 2026

Category: korean
Evaluated configuration: Yi 1.5 34B Chat
Evaluation type: human preference

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

Yi 1.5 34B Chat

1,143.19 rating

Confidence interval: 1,129.88 – 1,156.50

2098 votes

Oct 28, 2026

Category: longer_query
Evaluated configuration: Yi 1.5 34B Chat
Evaluation type: human preference

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

Yi 1.5 34B Chat

1,181.99 rating

Confidence interval: 1,170.94 – 1,193.04

2985 votes

Oct 28, 2026

Category: math
Evaluated configuration: Yi 1.5 34B Chat
Evaluation type: human preference

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

Yi 1.5 34B Chat

1,153.05 rating

Confidence interval: 1,141.80 – 1,164.31

3391 votes

Oct 28, 2026

Category: multi_turn
Evaluated configuration: Yi 1.5 34B Chat
Evaluation type: human preference

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

Yi 1.5 34B Chat

1,120.88 rating

Confidence interval: 1,113.81 – 1,127.95

11643 votes

Oct 28, 2026

Category: non_english
Evaluated configuration: Yi 1.5 34B Chat
Evaluation type: human preference

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

Yi 1.5 34B Chat

1,172.93 rating

Confidence interval: 1,167.94 – 1,177.93

24146 votes

Oct 28, 2026

Category: overall
Evaluated configuration: Yi 1.5 34B Chat
Evaluation type: human preference

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

Yi 1.5 34B Chat

1,090.79 rating

Confidence interval: 1,078.92 – 1,102.65

3231 votes

Oct 28, 2026

Category: russian
Evaluated configuration: Yi 1.5 34B Chat
Evaluation type: human preference

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

Yi 1.5 34B Chat

1,120.67 rating

Confidence interval: 1,089.76 – 1,151.58

458 votes

Oct 28, 2026

Category: spanish
Evaluated configuration: Yi 1.5 34B Chat
Evaluation type: human preference

Run it locally

Inference · memory estimate

Yi 1.5 34B Chat

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Model license: Apache-2.0