GeekRadar / The comparison desk
COMPARE.
AI models
google

gemini-2.5-flash-preview-09-2025

Model evaluation

Capability & preference

Human preference · Arena

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

gemini-2.5-flash-preview-09-2025 1406.5 gemini-2.5-flash-preview-09-2025 · 95% interval 1402.4–1410.5 · 32,995 votes · 2026-10-15

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 · 2026-10-15 · rating

gemini-2.5-flash-preview-09-2025

1,449.14 rating

Confidence interval: 1,437.01 – 1,461.27

2373 votes

Category
chinese
Evaluated configuration
gemini-2.5-flash-preview-09-2025
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating

gemini-2.5-flash-preview-09-2025

1,400.27 rating

Confidence interval: 1,392.87 – 1,407.67

6915 votes

Category
coding
Evaluated configuration
gemini-2.5-flash-preview-09-2025
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating

gemini-2.5-flash-preview-09-2025

1,386.58 rating

Confidence interval: 1,377.56 – 1,395.60

4549 votes

Category
creative_writing
Evaluated configuration
gemini-2.5-flash-preview-09-2025
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating

gemini-2.5-flash-preview-09-2025

1,412.90 rating

Confidence interval: 1,407.33 – 1,418.47

14043 votes

Category
english
Evaluated configuration
gemini-2.5-flash-preview-09-2025
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating

gemini-2.5-flash-preview-09-2025

1,388.88 rating

Confidence interval: 1,383.36 – 1,394.41

23421 votes

Category
exclude_ties
Evaluated configuration
gemini-2.5-flash-preview-09-2025
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-15 · rating

gemini-2.5-flash-preview-09-2025

1,418.04 rating

Confidence interval: 1,404.18 – 1,431.90

1788 votes

Category
expert
Evaluated configuration
gemini-2.5-flash-preview-09-2025
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-10-15 · rating

gemini-2.5-flash-preview-09-2025

1,432.76 rating

Confidence interval: 1,408.10 – 1,457.43

588 votes

Category
french
Evaluated configuration
gemini-2.5-flash-preview-09-2025
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-15 · rating

gemini-2.5-flash-preview-09-2025

1,417.98 rating

Confidence interval: 1,394.81 – 1,441.16

657 votes

Category
german
Evaluated configuration
gemini-2.5-flash-preview-09-2025
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating

gemini-2.5-flash-preview-09-2025

1,408.83 rating

Confidence interval: 1,403.70 – 1,413.96

17744 votes

Category
hard_prompts
Evaluated configuration
gemini-2.5-flash-preview-09-2025
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating

gemini-2.5-flash-preview-09-2025

1,410.33 rating

Confidence interval: 1,403.19 – 1,417.47

7548 votes

Category
hard_prompts_english
Evaluated configuration
gemini-2.5-flash-preview-09-2025
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating

gemini-2.5-flash-preview-09-2025

1,398.05 rating

Confidence interval: 1,390.23 – 1,405.88

6152 votes

Category
industry_business_and_management_and_financial_operations
Evaluated configuration
gemini-2.5-flash-preview-09-2025
Evaluation type
human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating

gemini-2.5-flash-preview-09-2025

1,385.71 rating

Confidence interval: 1,377.86 – 1,393.56

6070 votes

Category
industry_entertainment_and_sports_and_media
Evaluated configuration
gemini-2.5-flash-preview-09-2025
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating

gemini-2.5-flash-preview-09-2025

1,427.35 rating

Confidence interval: 1,414.82 – 1,439.88

2154 votes

Category
industry_legal_and_government
Evaluated configuration
gemini-2.5-flash-preview-09-2025
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating

gemini-2.5-flash-preview-09-2025

1,434.44 rating

Confidence interval: 1,426.12 – 1,442.76

5219 votes

Category
industry_life_and_physical_and_social_science
Evaluated configuration
gemini-2.5-flash-preview-09-2025
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating

gemini-2.5-flash-preview-09-2025

1,419.83 rating

Confidence interval: 1,405.81 – 1,433.86

1705 votes

Category
industry_mathematical
Evaluated configuration
gemini-2.5-flash-preview-09-2025
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating

gemini-2.5-flash-preview-09-2025

1,424.92 rating

Confidence interval: 1,410.49 – 1,439.35

1702 votes

Category
industry_medicine_and_healthcare
Evaluated configuration
gemini-2.5-flash-preview-09-2025
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating

gemini-2.5-flash-preview-09-2025

1,408.46 rating

Confidence interval: 1,402.45 – 1,414.46

11709 votes

Category
industry_software_and_it_services
Evaluated configuration
gemini-2.5-flash-preview-09-2025
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating

gemini-2.5-flash-preview-09-2025

1,395.16 rating

Confidence interval: 1,387.87 – 1,402.45

7376 votes

Category
industry_writing_and_literature_and_language
Evaluated configuration
gemini-2.5-flash-preview-09-2025
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating

gemini-2.5-flash-preview-09-2025

1,393.61 rating

Confidence interval: 1,387.06 – 1,400.15

9351 votes

Category
instruction_following
Evaluated configuration
gemini-2.5-flash-preview-09-2025
Evaluation type
human preference
Arena text preference / japanesehuman preference · 2026-10-15 · rating

gemini-2.5-flash-preview-09-2025

1,404.69 rating

Confidence interval: 1,373.22 – 1,436.16

359 votes

Category
japanese
Evaluated configuration
gemini-2.5-flash-preview-09-2025
Evaluation type
human preference
Arena text preference / koreanhuman preference · 2026-10-15 · rating

gemini-2.5-flash-preview-09-2025

1,384.54 rating

Confidence interval: 1,361.79 – 1,407.28

702 votes

Category
korean
Evaluated configuration
gemini-2.5-flash-preview-09-2025
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating

gemini-2.5-flash-preview-09-2025

1,405.59 rating

Confidence interval: 1,398.69 – 1,412.49

8238 votes

Category
longer_query
Evaluated configuration
gemini-2.5-flash-preview-09-2025
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating

gemini-2.5-flash-preview-09-2025

1,415.21 rating

Confidence interval: 1,402.29 – 1,428.13

1979 votes

Category
math
Evaluated configuration
gemini-2.5-flash-preview-09-2025
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating

gemini-2.5-flash-preview-09-2025

1,396.50 rating

Confidence interval: 1,388.44 – 1,404.56

5741 votes

Category
multi_turn
Evaluated configuration
gemini-2.5-flash-preview-09-2025
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating

gemini-2.5-flash-preview-09-2025

1,395.72 rating

Confidence interval: 1,390.72 – 1,400.71

18903 votes

Category
non_english
Evaluated configuration
gemini-2.5-flash-preview-09-2025
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating

gemini-2.5-flash-preview-09-2025

1,406.46 rating

Confidence interval: 1,402.44 – 1,410.48

32995 votes

Category
overall
Evaluated configuration
gemini-2.5-flash-preview-09-2025
Evaluation type
human preference
Arena text preference / polishhuman preference · 2026-10-15 · rating

gemini-2.5-flash-preview-09-2025

1,409.54 rating

Confidence interval: 1,393.11 – 1,425.96

1274 votes

Category
polish
Evaluated configuration
gemini-2.5-flash-preview-09-2025
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-10-15 · rating

gemini-2.5-flash-preview-09-2025

1,392.53 rating

Confidence interval: 1,382.04 – 1,403.01

2943 votes

Category
russian
Evaluated configuration
gemini-2.5-flash-preview-09-2025
Evaluation type
human preference
Arena text preference / spanishhuman preference · 2026-10-15 · rating

gemini-2.5-flash-preview-09-2025

1,404.63 rating

Confidence interval: 1,384.99 – 1,424.26

980 votes

Category
spanish
Evaluated configuration
gemini-2.5-flash-preview-09-2025
Evaluation type
human preference

Run it locally

Inference · memory estimate

gemini-2.5-flash-preview-09-2025

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Model license
Proprietary