GeekRadar / The comparison desk
COMPARE.
AI models
google

Gemini 2.5 Flash-Lite Preview (Thinking, 06-17)

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 (Thinking, 06-17) 1369.2 Gemini 2.5 Flash-Lite Preview (Thinking, 06-17) · 95% interval 1364.7–1373.7 · 32,381 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 (Thinking, 06-17)

1,400.14 rating

Confidence interval: 1,387.61 – 1,412.66

2264 votes

Category
chinese
Evaluated configuration
Gemini 2.5 Flash-Lite Preview (Thinking, 06-17)
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating

Gemini 2.5 Flash-Lite Preview (Thinking, 06-17)

1,372.52 rating

Confidence interval: 1,364.62 – 1,380.43

5978 votes

Category
coding
Evaluated configuration
Gemini 2.5 Flash-Lite Preview (Thinking, 06-17)
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating

Gemini 2.5 Flash-Lite Preview (Thinking, 06-17)

1,366.79 rating

Confidence interval: 1,357.50 – 1,376.09

4145 votes

Category
creative_writing
Evaluated configuration
Gemini 2.5 Flash-Lite Preview (Thinking, 06-17)
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating

Gemini 2.5 Flash-Lite Preview (Thinking, 06-17)

1,372.70 rating

Confidence interval: 1,366.90 – 1,378.50

14057 votes

Category
english
Evaluated configuration
Gemini 2.5 Flash-Lite Preview (Thinking, 06-17)
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating

Gemini 2.5 Flash-Lite Preview (Thinking, 06-17)

1,336.42 rating

Confidence interval: 1,330.31 – 1,342.53

22770 votes

Category
exclude_ties
Evaluated configuration
Gemini 2.5 Flash-Lite Preview (Thinking, 06-17)
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-28 · rating

Gemini 2.5 Flash-Lite Preview (Thinking, 06-17)

1,366.18 rating

Confidence interval: 1,351.69 – 1,380.68

1640 votes

Category
expert
Evaluated configuration
Gemini 2.5 Flash-Lite Preview (Thinking, 06-17)
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-10-28 · rating

Gemini 2.5 Flash-Lite Preview (Thinking, 06-17)

1,387.19 rating

Confidence interval: 1,358.60 – 1,415.79

444 votes

Category
french
Evaluated configuration
Gemini 2.5 Flash-Lite Preview (Thinking, 06-17)
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-28 · rating

Gemini 2.5 Flash-Lite Preview (Thinking, 06-17)

1,373.50 rating

Confidence interval: 1,352.91 – 1,394.09

843 votes

Category
german
Evaluated configuration
Gemini 2.5 Flash-Lite Preview (Thinking, 06-17)
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating

Gemini 2.5 Flash-Lite Preview (Thinking, 06-17)

1,373.61 rating

Confidence interval: 1,367.83 – 1,379.38

14495 votes

Category
hard_prompts
Evaluated configuration
Gemini 2.5 Flash-Lite Preview (Thinking, 06-17)
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating

Gemini 2.5 Flash-Lite Preview (Thinking, 06-17)

1,375.58 rating

Confidence interval: 1,367.87 – 1,383.29

6463 votes

Category
hard_prompts_english
Evaluated configuration
Gemini 2.5 Flash-Lite Preview (Thinking, 06-17)
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 (Thinking, 06-17)

1,353.85 rating

Confidence interval: 1,345.52 – 1,362.18

5432 votes

Category
industry_business_and_management_and_financial_operations
Evaluated configuration
Gemini 2.5 Flash-Lite Preview (Thinking, 06-17)
Evaluation type
human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating

Gemini 2.5 Flash-Lite Preview (Thinking, 06-17)

1,354.58 rating

Confidence interval: 1,346.59 – 1,362.57

5803 votes

Category
industry_entertainment_and_sports_and_media
Evaluated configuration
Gemini 2.5 Flash-Lite Preview (Thinking, 06-17)
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-28 · rating

Gemini 2.5 Flash-Lite Preview (Thinking, 06-17)

1,373.00 rating

Confidence interval: 1,359.94 – 1,386.05

2055 votes

Category
industry_legal_and_government
Evaluated configuration
Gemini 2.5 Flash-Lite Preview (Thinking, 06-17)
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 (Thinking, 06-17)

1,373.31 rating

Confidence interval: 1,364.84 – 1,381.77

5215 votes

Category
industry_life_and_physical_and_social_science
Evaluated configuration
Gemini 2.5 Flash-Lite Preview (Thinking, 06-17)
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating

Gemini 2.5 Flash-Lite Preview (Thinking, 06-17)

1,366.79 rating

Confidence interval: 1,353.93 – 1,379.66

1986 votes

Category
industry_mathematical
Evaluated configuration
Gemini 2.5 Flash-Lite Preview (Thinking, 06-17)
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating

Gemini 2.5 Flash-Lite Preview (Thinking, 06-17)

1,389.29 rating

Confidence interval: 1,375.62 – 1,402.96

1964 votes

Category
industry_medicine_and_healthcare
Evaluated configuration
Gemini 2.5 Flash-Lite Preview (Thinking, 06-17)
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating

Gemini 2.5 Flash-Lite Preview (Thinking, 06-17)

1,375.69 rating

Confidence interval: 1,369.30 – 1,382.07

10727 votes

Category
industry_software_and_it_services
Evaluated configuration
Gemini 2.5 Flash-Lite Preview (Thinking, 06-17)
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating

Gemini 2.5 Flash-Lite Preview (Thinking, 06-17)

1,374.86 rating

Confidence interval: 1,367.41 – 1,382.30

7064 votes

Category
industry_writing_and_literature_and_language
Evaluated configuration
Gemini 2.5 Flash-Lite Preview (Thinking, 06-17)
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating

Gemini 2.5 Flash-Lite Preview (Thinking, 06-17)

1,366.59 rating

Confidence interval: 1,359.62 – 1,373.56

8108 votes

Category
instruction_following
Evaluated configuration
Gemini 2.5 Flash-Lite Preview (Thinking, 06-17)
Evaluation type
human preference
Arena text preference / japanesehuman preference · 2026-10-28 · rating

Gemini 2.5 Flash-Lite Preview (Thinking, 06-17)

1,349.87 rating

Confidence interval: 1,328.65 – 1,371.09

807 votes

Category
japanese
Evaluated configuration
Gemini 2.5 Flash-Lite Preview (Thinking, 06-17)
Evaluation type
human preference
Arena text preference / koreanhuman preference · 2026-10-28 · rating

Gemini 2.5 Flash-Lite Preview (Thinking, 06-17)

1,360.12 rating

Confidence interval: 1,337.56 – 1,382.68

727 votes

Category
korean
Evaluated configuration
Gemini 2.5 Flash-Lite Preview (Thinking, 06-17)
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-10-28 · rating

Gemini 2.5 Flash-Lite Preview (Thinking, 06-17)

1,373.16 rating

Confidence interval: 1,365.40 – 1,380.93

6397 votes

Category
longer_query
Evaluated configuration
Gemini 2.5 Flash-Lite Preview (Thinking, 06-17)
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-10-28 · rating

Gemini 2.5 Flash-Lite Preview (Thinking, 06-17)

1,362.15 rating

Confidence interval: 1,349.72 – 1,374.58

2073 votes

Category
math
Evaluated configuration
Gemini 2.5 Flash-Lite Preview (Thinking, 06-17)
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-10-28 · rating

Gemini 2.5 Flash-Lite Preview (Thinking, 06-17)

1,359.55 rating

Confidence interval: 1,351.22 – 1,367.89

5468 votes

Category
multi_turn
Evaluated configuration
Gemini 2.5 Flash-Lite Preview (Thinking, 06-17)
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-10-28 · rating

Gemini 2.5 Flash-Lite Preview (Thinking, 06-17)

1,359.98 rating

Confidence interval: 1,354.59 – 1,365.38

18312 votes

Category
non_english
Evaluated configuration
Gemini 2.5 Flash-Lite Preview (Thinking, 06-17)
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-10-28 · rating

Gemini 2.5 Flash-Lite Preview (Thinking, 06-17)

1,369.21 rating

Confidence interval: 1,364.72 – 1,373.69

32381 votes

Category
overall
Evaluated configuration
Gemini 2.5 Flash-Lite Preview (Thinking, 06-17)
Evaluation type
human preference
Arena text preference / polishhuman preference · 2026-10-28 · rating

Gemini 2.5 Flash-Lite Preview (Thinking, 06-17)

1,361.47 rating

Confidence interval: 1,349.89 – 1,373.05

2957 votes

Category
polish
Evaluated configuration
Gemini 2.5 Flash-Lite Preview (Thinking, 06-17)
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-10-28 · rating

Gemini 2.5 Flash-Lite Preview (Thinking, 06-17)

1,363.69 rating

Confidence interval: 1,351.73 – 1,375.64

2274 votes

Category
russian
Evaluated configuration
Gemini 2.5 Flash-Lite Preview (Thinking, 06-17)
Evaluation type
human preference
Arena text preference / spanishhuman preference · 2026-10-28 · rating

Gemini 2.5 Flash-Lite Preview (Thinking, 06-17)

1,364.69 rating

Confidence interval: 1,343.40 – 1,385.98

808 votes

Category
spanish
Evaluated configuration
Gemini 2.5 Flash-Lite Preview (Thinking, 06-17)
Evaluation type
human preference

Run it locally

Inference · memory estimate

Gemini 2.5 Flash-Lite Preview (Thinking, 06-17)

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Model license
Proprietary