GeekRadar / The comparison desk

COMPARE.

AI models

google

Gemini Pro (Dev API)

Model evaluation

Capability & preference

Human preference · Arena

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

Gemini Pro (Dev API) 1148.8 Gemini Pro (Dev API) · 95% interval 1141.6–1156.0 · 18,354 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

Gemini Pro (Dev API)

1,123.99 rating

Confidence interval: 1,106.65 – 1,141.32

1867 votes

Oct 28, 2026

Category: chinese
Evaluated configuration: Gemini Pro (Dev API)
Evaluation type: human preference

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

Gemini Pro (Dev API)

1,103.70 rating

Confidence interval: 1,089.97 – 1,117.43

2681 votes

Oct 28, 2026

Category: coding
Evaluated configuration: Gemini Pro (Dev API)
Evaluation type: human preference

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

Gemini Pro (Dev API)

1,130.15 rating

Confidence interval: 1,116.36 – 1,143.94

3046 votes

Oct 28, 2026

Category: creative_writing
Evaluated configuration: Gemini Pro (Dev API)
Evaluation type: human preference

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

Gemini Pro (Dev API)

1,161.84 rating

Confidence interval: 1,153.45 – 1,170.22

12477 votes

Oct 28, 2026

Category: english
Evaluated configuration: Gemini Pro (Dev API)
Evaluation type: human preference

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

Gemini Pro (Dev API)

1,007.88 rating

Confidence interval: 997.45 – 1,018.31

12956 votes

Oct 28, 2026

Category: exclude_ties
Evaluated configuration: Gemini Pro (Dev API)
Evaluation type: human preference

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

Gemini Pro (Dev API)

1,058.82 rating

Confidence interval: 1,035.64 – 1,081.99

694 votes

Oct 28, 2026

Category: expert
Evaluated configuration: Gemini Pro (Dev API)
Evaluation type: human preference

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

Gemini Pro (Dev API)

1,145.40 rating

Confidence interval: 1,112.82 – 1,177.97

462 votes

Oct 28, 2026

Category: french
Evaluated configuration: Gemini Pro (Dev API)
Evaluation type: human preference

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

Gemini Pro (Dev API)

1,124.53 rating

Confidence interval: 1,094.77 – 1,154.28

450 votes

Oct 28, 2026

Category: german
Evaluated configuration: Gemini Pro (Dev API)
Evaluation type: human preference

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

Gemini Pro (Dev API)

1,109.18 rating

Confidence interval: 1,098.03 – 1,120.34

4515 votes

Oct 28, 2026

Category: hard_prompts
Evaluated configuration: Gemini Pro (Dev API)
Evaluation type: human preference

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

Gemini Pro (Dev API)

1,116.81 rating

Confidence interval: 1,104.29 – 1,129.34

3298 votes

Oct 28, 2026

Category: hard_prompts_english
Evaluated configuration: Gemini Pro (Dev API)
Evaluation type: human preference

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

Gemini Pro (Dev API)

1,130.65 rating

Confidence interval: 1,113.64 – 1,147.67

1672 votes

Oct 28, 2026

Category: industry_business_and_management_and_financial_operations
Evaluated configuration: Gemini Pro (Dev API)
Evaluation type: human preference

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

Gemini Pro (Dev API)

1,099.59 rating

Confidence interval: 1,085.68 – 1,113.50

2882 votes

Oct 28, 2026

Category: industry_entertainment_and_sports_and_media
Evaluated configuration: Gemini Pro (Dev API)
Evaluation type: human preference

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

Gemini Pro (Dev API)

1,166.31 rating

Confidence interval: 1,145.12 – 1,187.51

970 votes

Oct 28, 2026

Category: industry_legal_and_government
Evaluated configuration: Gemini Pro (Dev API)
Evaluation type: human preference

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

Gemini Pro (Dev API)

1,143.84 rating

Confidence interval: 1,130.26 – 1,157.42

3251 votes

Oct 28, 2026

Category: industry_life_and_physical_and_social_science
Evaluated configuration: Gemini Pro (Dev API)
Evaluation type: human preference

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

Gemini Pro (Dev API)

1,123.74 rating

Confidence interval: 1,108.81 – 1,138.67

1975 votes

Oct 28, 2026

Category: industry_mathematical
Evaluated configuration: Gemini Pro (Dev API)
Evaluation type: human preference

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

Gemini Pro (Dev API)

1,134.63 rating

Confidence interval: 1,114.08 – 1,155.18

1076 votes

Oct 28, 2026

Category: industry_medicine_and_healthcare
Evaluated configuration: Gemini Pro (Dev API)
Evaluation type: human preference

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

Gemini Pro (Dev API)

1,131.02 rating

Confidence interval: 1,119.67 – 1,142.37

4907 votes

Oct 28, 2026

Category: industry_software_and_it_services
Evaluated configuration: Gemini Pro (Dev API)
Evaluation type: human preference

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

Gemini Pro (Dev API)

1,143.90 rating

Confidence interval: 1,132.10 – 1,155.69

4634 votes

Oct 28, 2026

Category: industry_writing_and_literature_and_language
Evaluated configuration: Gemini Pro (Dev API)
Evaluation type: human preference

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

Gemini Pro (Dev API)

1,113.98 rating

Confidence interval: 1,103.53 – 1,124.44

5876 votes

Oct 28, 2026

Category: instruction_following
Evaluated configuration: Gemini Pro (Dev API)
Evaluation type: human preference

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

Gemini Pro (Dev API)

1,022.72 rating

Confidence interval: 977.85 – 1,067.59

173 votes

Oct 28, 2026

Category: japanese
Evaluated configuration: Gemini Pro (Dev API)
Evaluation type: human preference

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

Gemini Pro (Dev API)

1,131.36 rating

Confidence interval: 1,113.77 – 1,148.96

1351 votes

Oct 28, 2026

Category: longer_query
Evaluated configuration: Gemini Pro (Dev API)
Evaluation type: human preference

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

Gemini Pro (Dev API)

1,132.04 rating

Confidence interval: 1,118.20 – 1,145.88

2274 votes

Oct 28, 2026

Category: math
Evaluated configuration: Gemini Pro (Dev API)
Evaluation type: human preference

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

Gemini Pro (Dev API)

1,124.23 rating

Confidence interval: 1,109.73 – 1,138.73

2528 votes

Oct 28, 2026

Category: multi_turn
Evaluated configuration: Gemini Pro (Dev API)
Evaluation type: human preference

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

Gemini Pro (Dev API)

1,137.86 rating

Confidence interval: 1,127.23 – 1,148.49

5877 votes

Oct 28, 2026

Category: non_english
Evaluated configuration: Gemini Pro (Dev API)
Evaluation type: human preference

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

Gemini Pro (Dev API)

1,148.82 rating

Confidence interval: 1,141.63 – 1,156.02

18354 votes

Oct 28, 2026

Category: overall
Evaluated configuration: Gemini Pro (Dev API)
Evaluation type: human preference

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

Gemini Pro (Dev API)

1,185.83 rating

Confidence interval: 1,165.76 – 1,205.90

953 votes

Oct 28, 2026

Category: russian
Evaluated configuration: Gemini Pro (Dev API)
Evaluation type: human preference

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

Gemini Pro (Dev API)

1,118.93 rating

Confidence interval: 1,077.34 – 1,160.52

213 votes

Oct 28, 2026

Category: spanish
Evaluated configuration: Gemini Pro (Dev API)
Evaluation type: human preference

Run it locally

Inference · memory estimate

Gemini Pro (Dev API)

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Model license: Proprietary