GeekRadar / The comparison desk
COMPARE.
AI models
google

Gemini 2.5 Flash-Lite Preview (Non-Thinking, 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-Lite Preview (Non-Thinking, 09-2025) 1379.3 Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025) · 95% interval 1375.9–1382.7 · 47,418 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 2.5 Flash-Lite Preview (Non-Thinking, 09-2025)

1,404.25 rating

Confidence interval: 1,394.31 – 1,414.19

3648 votes

Category
chinese
Evaluated configuration
Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025)
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating

Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025)

1,371.73 rating

Confidence interval: 1,365.39 – 1,378.07

9840 votes

Category
coding
Evaluated configuration
Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025)
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating

Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025)

1,358.22 rating

Confidence interval: 1,350.70 – 1,365.75

6626 votes

Category
creative_writing
Evaluated configuration
Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025)
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating

Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025)

1,383.11 rating

Confidence interval: 1,378.34 – 1,387.87

20059 votes

Category
english
Evaluated configuration
Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025)
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating

Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025)

1,349.67 rating

Confidence interval: 1,344.89 – 1,354.46

33186 votes

Category
exclude_ties
Evaluated configuration
Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025)
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-28 · rating

Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025)

1,373.76 rating

Confidence interval: 1,362.87 – 1,384.64

2842 votes

Category
expert
Evaluated configuration
Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025)
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-10-28 · rating

Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025)

1,389.03 rating

Confidence interval: 1,368.34 – 1,409.72

840 votes

Category
french
Evaluated configuration
Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025)
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-28 · rating

Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025)

1,388.68 rating

Confidence interval: 1,368.31 – 1,409.05

845 votes

Category
german
Evaluated configuration
Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025)
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating

Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025)

1,377.08 rating

Confidence interval: 1,372.70 – 1,381.46

25522 votes

Category
hard_prompts
Evaluated configuration
Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025)
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating

Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025)

1,383.10 rating

Confidence interval: 1,376.98 – 1,389.21

10694 votes

Category
hard_prompts_english
Evaluated configuration
Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025)
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating

Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025)

1,367.34 rating

Confidence interval: 1,360.78 – 1,373.89

9097 votes

Category
industry_business_and_management_and_financial_operations
Evaluated configuration
Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025)
Evaluation type
human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating

Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025)

1,344.48 rating

Confidence interval: 1,337.84 – 1,351.12

8654 votes

Category
industry_entertainment_and_sports_and_media
Evaluated configuration
Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025)
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-28 · rating

Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025)

1,391.24 rating

Confidence interval: 1,380.89 – 1,401.59

3175 votes

Category
industry_legal_and_government
Evaluated configuration
Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025)
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating

Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025)

1,395.37 rating

Confidence interval: 1,388.36 – 1,402.38

7599 votes

Category
industry_life_and_physical_and_social_science
Evaluated configuration
Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025)
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating

Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025)

1,376.95 rating

Confidence interval: 1,364.72 – 1,389.18

2242 votes

Category
industry_mathematical
Evaluated configuration
Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025)
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating

Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025)

1,388.36 rating

Confidence interval: 1,376.60 – 1,400.12

2585 votes

Category
industry_medicine_and_healthcare
Evaluated configuration
Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025)
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating

Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025)

1,384.07 rating

Confidence interval: 1,378.91 – 1,389.23

16598 votes

Category
industry_software_and_it_services
Evaluated configuration
Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025)
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating

Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025)

1,368.29 rating

Confidence interval: 1,362.12 – 1,374.46

10640 votes

Category
industry_writing_and_literature_and_language
Evaluated configuration
Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025)
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating

Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025)

1,355.30 rating

Confidence interval: 1,349.70 – 1,360.90

13251 votes

Category
instruction_following
Evaluated configuration
Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025)
Evaluation type
human preference
Arena text preference / japanesehuman preference · 2026-10-28 · rating

Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025)

1,359.17 rating

Confidence interval: 1,333.06 – 1,385.29

502 votes

Category
japanese
Evaluated configuration
Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025)
Evaluation type
human preference
Arena text preference / koreanhuman preference · 2026-10-28 · rating

Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025)

1,349.81 rating

Confidence interval: 1,328.71 – 1,370.91

798 votes

Category
korean
Evaluated configuration
Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025)
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-10-28 · rating

Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025)

1,372.72 rating

Confidence interval: 1,366.88 – 1,378.57

11986 votes

Category
longer_query
Evaluated configuration
Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025)
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-10-28 · rating

Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025)

1,373.14 rating

Confidence interval: 1,362.48 – 1,383.79

2953 votes

Category
math
Evaluated configuration
Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025)
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-10-28 · rating

Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025)

1,366.23 rating

Confidence interval: 1,359.27 – 1,373.19

8130 votes

Category
multi_turn
Evaluated configuration
Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025)
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-10-28 · rating

Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025)

1,368.74 rating

Confidence interval: 1,364.48 – 1,372.99

27323 votes

Category
non_english
Evaluated configuration
Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025)
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-10-28 · rating

Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025)

1,379.29 rating

Confidence interval: 1,375.90 – 1,382.69

47418 votes

Category
overall
Evaluated configuration
Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025)
Evaluation type
human preference
Arena text preference / polishhuman preference · 2026-10-28 · rating

Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025)

1,370.89 rating

Confidence interval: 1,356.60 – 1,385.18

1630 votes

Category
polish
Evaluated configuration
Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025)
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-10-28 · rating

Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025)

1,372.74 rating

Confidence interval: 1,364.38 – 1,381.09

4794 votes

Category
russian
Evaluated configuration
Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025)
Evaluation type
human preference
Arena text preference / spanishhuman preference · 2026-10-28 · rating

Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025)

1,395.65 rating

Confidence interval: 1,379.66 – 1,411.63

1434 votes

Category
spanish
Evaluated configuration
Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025)
Evaluation type
human preference

Run it locally

Inference · memory estimate

Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025)

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Model license
Proprietary