GeekRadar / The comparison desk
COMPARE.
AI models
google

Gemini 2.0 Flash (001)

Model evaluation

Capability & preference

Human preference · Arena

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

Gemini 2.0 Flash (001) 1354.0 Gemini 2.0 Flash (001) · 95% interval 1350.3–1357.8 · 43,443 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 2.0 Flash (001)

1,372.64 rating

Confidence interval: 1,361.17 – 1,384.10

2697 votes

Category
chinese
Evaluated configuration
Gemini 2.0 Flash (001)
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating

Gemini 2.0 Flash (001)

1,350.18 rating

Confidence interval: 1,342.97 – 1,357.39

6960 votes

Category
coding
Evaluated configuration
Gemini 2.0 Flash (001)
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating

Gemini 2.0 Flash (001)

1,339.19 rating

Confidence interval: 1,331.49 – 1,346.88

6274 votes

Category
creative_writing
Evaluated configuration
Gemini 2.0 Flash (001)
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating

Gemini 2.0 Flash (001)

1,365.44 rating

Confidence interval: 1,360.79 – 1,370.10

23806 votes

Category
english
Evaluated configuration
Gemini 2.0 Flash (001)
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating

Gemini 2.0 Flash (001)

1,317.34 rating

Confidence interval: 1,312.09 – 1,322.59

29893 votes

Category
exclude_ties
Evaluated configuration
Gemini 2.0 Flash (001)
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-28 · rating

Gemini 2.0 Flash (001)

1,339.03 rating

Confidence interval: 1,326.56 – 1,351.50

2209 votes

Category
expert
Evaluated configuration
Gemini 2.0 Flash (001)
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-10-28 · rating

Gemini 2.0 Flash (001)

1,391.63 rating

Confidence interval: 1,365.71 – 1,417.55

540 votes

Category
french
Evaluated configuration
Gemini 2.0 Flash (001)
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-28 · rating

Gemini 2.0 Flash (001)

1,353.25 rating

Confidence interval: 1,335.44 – 1,371.05

1069 votes

Category
german
Evaluated configuration
Gemini 2.0 Flash (001)
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating

Gemini 2.0 Flash (001)

1,346.18 rating

Confidence interval: 1,340.76 – 1,351.60

14068 votes

Category
hard_prompts
Evaluated configuration
Gemini 2.0 Flash (001)
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating

Gemini 2.0 Flash (001)

1,355.35 rating

Confidence interval: 1,348.52 – 1,362.19

7945 votes

Category
hard_prompts_english
Evaluated configuration
Gemini 2.0 Flash (001)
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating

Gemini 2.0 Flash (001)

1,336.33 rating

Confidence interval: 1,327.97 – 1,344.68

5261 votes

Category
industry_business_and_management_and_financial_operations
Evaluated configuration
Gemini 2.0 Flash (001)
Evaluation type
human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating

Gemini 2.0 Flash (001)

1,332.75 rating

Confidence interval: 1,325.81 – 1,339.68

7739 votes

Category
industry_entertainment_and_sports_and_media
Evaluated configuration
Gemini 2.0 Flash (001)
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-28 · rating

Gemini 2.0 Flash (001)

1,371.02 rating

Confidence interval: 1,359.22 – 1,382.83

2559 votes

Category
industry_legal_and_government
Evaluated configuration
Gemini 2.0 Flash (001)
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating

Gemini 2.0 Flash (001)

1,360.54 rating

Confidence interval: 1,353.45 – 1,367.62

7784 votes

Category
industry_life_and_physical_and_social_science
Evaluated configuration
Gemini 2.0 Flash (001)
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating

Gemini 2.0 Flash (001)

1,356.86 rating

Confidence interval: 1,347.47 – 1,366.25

3747 votes

Category
industry_mathematical
Evaluated configuration
Gemini 2.0 Flash (001)
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating

Gemini 2.0 Flash (001)

1,368.28 rating

Confidence interval: 1,355.55 – 1,381.00

2299 votes

Category
industry_medicine_and_healthcare
Evaluated configuration
Gemini 2.0 Flash (001)
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating

Gemini 2.0 Flash (001)

1,360.86 rating

Confidence interval: 1,355.07 – 1,366.65

12122 votes

Category
industry_software_and_it_services
Evaluated configuration
Gemini 2.0 Flash (001)
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating

Gemini 2.0 Flash (001)

1,346.89 rating

Confidence interval: 1,340.76 – 1,353.02

10539 votes

Category
industry_writing_and_literature_and_language
Evaluated configuration
Gemini 2.0 Flash (001)
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating

Gemini 2.0 Flash (001)

1,335.83 rating

Confidence interval: 1,330.30 – 1,341.36

13645 votes

Category
instruction_following
Evaluated configuration
Gemini 2.0 Flash (001)
Evaluation type
human preference
Arena text preference / japanesehuman preference · 2026-10-28 · rating

Gemini 2.0 Flash (001)

1,293.84 rating

Confidence interval: 1,274.96 – 1,312.71

1026 votes

Category
japanese
Evaluated configuration
Gemini 2.0 Flash (001)
Evaluation type
human preference
Arena text preference / koreanhuman preference · 2026-10-28 · rating

Gemini 2.0 Flash (001)

1,312.83 rating

Confidence interval: 1,289.40 – 1,336.27

663 votes

Category
korean
Evaluated configuration
Gemini 2.0 Flash (001)
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-10-28 · rating

Gemini 2.0 Flash (001)

1,344.24 rating

Confidence interval: 1,336.84 – 1,351.65

6523 votes

Category
longer_query
Evaluated configuration
Gemini 2.0 Flash (001)
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-10-28 · rating

Gemini 2.0 Flash (001)

1,351.82 rating

Confidence interval: 1,342.80 – 1,360.85

4059 votes

Category
math
Evaluated configuration
Gemini 2.0 Flash (001)
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-10-28 · rating

Gemini 2.0 Flash (001)

1,349.59 rating

Confidence interval: 1,342.20 – 1,356.98

6827 votes

Category
multi_turn
Evaluated configuration
Gemini 2.0 Flash (001)
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-10-28 · rating

Gemini 2.0 Flash (001)

1,342.04 rating

Confidence interval: 1,337.20 – 1,346.87

19632 votes

Category
non_english
Evaluated configuration
Gemini 2.0 Flash (001)
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-10-28 · rating

Gemini 2.0 Flash (001)

1,354.04 rating

Confidence interval: 1,350.30 – 1,357.79

43443 votes

Category
overall
Evaluated configuration
Gemini 2.0 Flash (001)
Evaluation type
human preference
Arena text preference / polishhuman preference · 2026-10-28 · rating

Gemini 2.0 Flash (001)

1,349.03 rating

Confidence interval: 1,332.85 – 1,365.21

1350 votes

Category
polish
Evaluated configuration
Gemini 2.0 Flash (001)
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-10-28 · rating

Gemini 2.0 Flash (001)

1,351.30 rating

Confidence interval: 1,341.76 – 1,360.84

3711 votes

Category
russian
Evaluated configuration
Gemini 2.0 Flash (001)
Evaluation type
human preference
Arena text preference / spanishhuman preference · 2026-10-28 · rating

Gemini 2.0 Flash (001)

1,363.24 rating

Confidence interval: 1,338.24 – 1,388.24

553 votes

Category
spanish
Evaluated configuration
Gemini 2.0 Flash (001)
Evaluation type
human preference

Run it locally

Inference · memory estimate

Gemini 2.0 Flash (001)

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Model license
Proprietary