GeekRadar / The comparison desk
COMPARE.
AI models
google

Gemini 1.5 Flash-8B (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 1.5 Flash-8B (001) 1225.8 Gemini 1.5 Flash-8B (001) · 95% interval 1221.6–1230.1 · 35,558 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 1.5 Flash-8B (001)

1,230.81 rating

Confidence interval: 1,219.16 – 1,242.45

2914 votes

Category
chinese
Evaluated configuration
Gemini 1.5 Flash-8B (001)
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating

Gemini 1.5 Flash-8B (001)

1,217.35 rating

Confidence interval: 1,209.32 – 1,225.38

6069 votes

Category
coding
Evaluated configuration
Gemini 1.5 Flash-8B (001)
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating

Gemini 1.5 Flash-8B (001)

1,217.21 rating

Confidence interval: 1,208.37 – 1,226.04

5031 votes

Category
creative_writing
Evaluated configuration
Gemini 1.5 Flash-8B (001)
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating

Gemini 1.5 Flash-8B (001)

1,231.29 rating

Confidence interval: 1,225.76 – 1,236.82

18467 votes

Category
english
Evaluated configuration
Gemini 1.5 Flash-8B (001)
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating

Gemini 1.5 Flash-8B (001)

1,117.72 rating

Confidence interval: 1,110.95 – 1,124.48

22722 votes

Category
exclude_ties
Evaluated configuration
Gemini 1.5 Flash-8B (001)
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-28 · rating

Gemini 1.5 Flash-8B (001)

1,184.88 rating

Confidence interval: 1,171.85 – 1,197.90

2111 votes

Category
expert
Evaluated configuration
Gemini 1.5 Flash-8B (001)
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-10-28 · rating

Gemini 1.5 Flash-8B (001)

1,234.27 rating

Confidence interval: 1,201.16 – 1,267.39

331 votes

Category
french
Evaluated configuration
Gemini 1.5 Flash-8B (001)
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-28 · rating

Gemini 1.5 Flash-8B (001)

1,205.98 rating

Confidence interval: 1,184.85 – 1,227.11

798 votes

Category
german
Evaluated configuration
Gemini 1.5 Flash-8B (001)
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating

Gemini 1.5 Flash-8B (001)

1,209.29 rating

Confidence interval: 1,202.65 – 1,215.93

9654 votes

Category
hard_prompts
Evaluated configuration
Gemini 1.5 Flash-8B (001)
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating

Gemini 1.5 Flash-8B (001)

1,214.50 rating

Confidence interval: 1,206.30 – 1,222.69

5581 votes

Category
hard_prompts_english
Evaluated configuration
Gemini 1.5 Flash-8B (001)
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating

Gemini 1.5 Flash-8B (001)

1,210.82 rating

Confidence interval: 1,201.13 – 1,220.51

4291 votes

Category
industry_business_and_management_and_financial_operations
Evaluated configuration
Gemini 1.5 Flash-8B (001)
Evaluation type
human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating

Gemini 1.5 Flash-8B (001)

1,184.98 rating

Confidence interval: 1,176.55 – 1,193.41

5700 votes

Category
industry_entertainment_and_sports_and_media
Evaluated configuration
Gemini 1.5 Flash-8B (001)
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-28 · rating

Gemini 1.5 Flash-8B (001)

1,247.60 rating

Confidence interval: 1,234.15 – 1,261.05

2128 votes

Category
industry_legal_and_government
Evaluated configuration
Gemini 1.5 Flash-8B (001)
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating

Gemini 1.5 Flash-8B (001)

1,232.14 rating

Confidence interval: 1,223.80 – 1,240.48

6236 votes

Category
industry_life_and_physical_and_social_science
Evaluated configuration
Gemini 1.5 Flash-8B (001)
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating

Gemini 1.5 Flash-8B (001)

1,225.67 rating

Confidence interval: 1,216.57 – 1,234.77

4171 votes

Category
industry_mathematical
Evaluated configuration
Gemini 1.5 Flash-8B (001)
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating

Gemini 1.5 Flash-8B (001)

1,213.65 rating

Confidence interval: 1,198.77 – 1,228.53

1813 votes

Category
industry_medicine_and_healthcare
Evaluated configuration
Gemini 1.5 Flash-8B (001)
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating

Gemini 1.5 Flash-8B (001)

1,227.17 rating

Confidence interval: 1,220.27 – 1,234.07

9602 votes

Category
industry_software_and_it_services
Evaluated configuration
Gemini 1.5 Flash-8B (001)
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating

Gemini 1.5 Flash-8B (001)

1,226.69 rating

Confidence interval: 1,219.62 – 1,233.75

9499 votes

Category
industry_writing_and_literature_and_language
Evaluated configuration
Gemini 1.5 Flash-8B (001)
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating

Gemini 1.5 Flash-8B (001)

1,198.94 rating

Confidence interval: 1,193.02 – 1,204.86

14894 votes

Category
instruction_following
Evaluated configuration
Gemini 1.5 Flash-8B (001)
Evaluation type
human preference
Arena text preference / japanesehuman preference · 2026-10-28 · rating

Gemini 1.5 Flash-8B (001)

1,150.18 rating

Confidence interval: 1,127.43 – 1,172.93

691 votes

Category
japanese
Evaluated configuration
Gemini 1.5 Flash-8B (001)
Evaluation type
human preference
Arena text preference / koreanhuman preference · 2026-10-28 · rating

Gemini 1.5 Flash-8B (001)

1,140.01 rating

Confidence interval: 1,111.15 – 1,168.87

500 votes

Category
korean
Evaluated configuration
Gemini 1.5 Flash-8B (001)
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-10-28 · rating

Gemini 1.5 Flash-8B (001)

1,218.30 rating

Confidence interval: 1,209.87 – 1,226.72

5573 votes

Category
longer_query
Evaluated configuration
Gemini 1.5 Flash-8B (001)
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-10-28 · rating

Gemini 1.5 Flash-8B (001)

1,206.63 rating

Confidence interval: 1,198.12 – 1,215.14

5036 votes

Category
math
Evaluated configuration
Gemini 1.5 Flash-8B (001)
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-10-28 · rating

Gemini 1.5 Flash-8B (001)

1,185.23 rating

Confidence interval: 1,176.82 – 1,193.65

6665 votes

Category
multi_turn
Evaluated configuration
Gemini 1.5 Flash-8B (001)
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-10-28 · rating

Gemini 1.5 Flash-8B (001)

1,214.48 rating

Confidence interval: 1,208.81 – 1,220.14

17091 votes

Category
non_english
Evaluated configuration
Gemini 1.5 Flash-8B (001)
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-10-28 · rating

Gemini 1.5 Flash-8B (001)

1,225.83 rating

Confidence interval: 1,221.55 – 1,230.11

35558 votes

Category
overall
Evaluated configuration
Gemini 1.5 Flash-8B (001)
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-10-28 · rating

Gemini 1.5 Flash-8B (001)

1,235.55 rating

Confidence interval: 1,226.83 – 1,244.26

5317 votes

Category
russian
Evaluated configuration
Gemini 1.5 Flash-8B (001)
Evaluation type
human preference
Arena text preference / spanishhuman preference · 2026-10-28 · rating

Gemini 1.5 Flash-8B (001)

1,212.34 rating

Confidence interval: 1,180.85 – 1,243.83

323 votes

Category
spanish
Evaluated configuration
Gemini 1.5 Flash-8B (001)
Evaluation type
human preference

Run it locally

Inference · memory estimate

Gemini 1.5 Flash-8B (001)

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Model license
Proprietary