GeekRadar / The comparison desk
COMPARE.
AI models
google

Gemini 1.5 Flash (002)

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 (002) 1286.6 Gemini 1.5 Flash (002) · 95% interval 1282.4–1290.8 · 34,902 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 (002)

1,294.74 rating

Confidence interval: 1,283.30 – 1,306.18

2980 votes

Category
chinese
Evaluated configuration
Gemini 1.5 Flash (002)
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating

Gemini 1.5 Flash (002)

1,261.24 rating

Confidence interval: 1,253.25 – 1,269.22

5892 votes

Category
coding
Evaluated configuration
Gemini 1.5 Flash (002)
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating

Gemini 1.5 Flash (002)

1,285.11 rating

Confidence interval: 1,276.22 – 1,294.00

5017 votes

Category
creative_writing
Evaluated configuration
Gemini 1.5 Flash (002)
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating

Gemini 1.5 Flash (002)

1,288.59 rating

Confidence interval: 1,283.18 – 1,294.00

18364 votes

Category
english
Evaluated configuration
Gemini 1.5 Flash (002)
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating

Gemini 1.5 Flash (002)

1,215.18 rating

Confidence interval: 1,208.71 – 1,221.66

22474 votes

Category
exclude_ties
Evaluated configuration
Gemini 1.5 Flash (002)
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-28 · rating

Gemini 1.5 Flash (002)

1,232.83 rating

Confidence interval: 1,219.76 – 1,245.89

2116 votes

Category
expert
Evaluated configuration
Gemini 1.5 Flash (002)
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-10-28 · rating

Gemini 1.5 Flash (002)

1,258.56 rating

Confidence interval: 1,224.13 – 1,293.00

295 votes

Category
french
Evaluated configuration
Gemini 1.5 Flash (002)
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-28 · rating

Gemini 1.5 Flash (002)

1,261.58 rating

Confidence interval: 1,240.07 – 1,283.08

739 votes

Category
german
Evaluated configuration
Gemini 1.5 Flash (002)
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating

Gemini 1.5 Flash (002)

1,257.10 rating

Confidence interval: 1,250.46 – 1,263.75

9262 votes

Category
hard_prompts
Evaluated configuration
Gemini 1.5 Flash (002)
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating

Gemini 1.5 Flash (002)

1,264.71 rating

Confidence interval: 1,256.56 – 1,272.87

5484 votes

Category
hard_prompts_english
Evaluated configuration
Gemini 1.5 Flash (002)
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating

Gemini 1.5 Flash (002)

1,264.45 rating

Confidence interval: 1,254.80 – 1,274.11

4259 votes

Category
industry_business_and_management_and_financial_operations
Evaluated configuration
Gemini 1.5 Flash (002)
Evaluation type
human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating

Gemini 1.5 Flash (002)

1,251.41 rating

Confidence interval: 1,243.24 – 1,259.59

5693 votes

Category
industry_entertainment_and_sports_and_media
Evaluated configuration
Gemini 1.5 Flash (002)
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-28 · rating

Gemini 1.5 Flash (002)

1,301.98 rating

Confidence interval: 1,288.58 – 1,315.38

2160 votes

Category
industry_legal_and_government
Evaluated configuration
Gemini 1.5 Flash (002)
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating

Gemini 1.5 Flash (002)

1,299.24 rating

Confidence interval: 1,290.91 – 1,307.56

6083 votes

Category
industry_life_and_physical_and_social_science
Evaluated configuration
Gemini 1.5 Flash (002)
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating

Gemini 1.5 Flash (002)

1,279.28 rating

Confidence interval: 1,270.03 – 1,288.53

4114 votes

Category
industry_mathematical
Evaluated configuration
Gemini 1.5 Flash (002)
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating

Gemini 1.5 Flash (002)

1,289.89 rating

Confidence interval: 1,274.90 – 1,304.88

1696 votes

Category
industry_medicine_and_healthcare
Evaluated configuration
Gemini 1.5 Flash (002)
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating

Gemini 1.5 Flash (002)

1,277.97 rating

Confidence interval: 1,271.13 – 1,284.81

9225 votes

Category
industry_software_and_it_services
Evaluated configuration
Gemini 1.5 Flash (002)
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating

Gemini 1.5 Flash (002)

1,293.35 rating

Confidence interval: 1,286.39 – 1,300.31

9441 votes

Category
industry_writing_and_literature_and_language
Evaluated configuration
Gemini 1.5 Flash (002)
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating

Gemini 1.5 Flash (002)

1,257.34 rating

Confidence interval: 1,251.47 – 1,263.21

14561 votes

Category
instruction_following
Evaluated configuration
Gemini 1.5 Flash (002)
Evaluation type
human preference
Arena text preference / japanesehuman preference · 2026-10-28 · rating

Gemini 1.5 Flash (002)

1,252.48 rating

Confidence interval: 1,230.52 – 1,274.45

753 votes

Category
japanese
Evaluated configuration
Gemini 1.5 Flash (002)
Evaluation type
human preference
Arena text preference / koreanhuman preference · 2026-10-28 · rating

Gemini 1.5 Flash (002)

1,220.49 rating

Confidence interval: 1,191.99 – 1,248.99

502 votes

Category
korean
Evaluated configuration
Gemini 1.5 Flash (002)
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-10-28 · rating

Gemini 1.5 Flash (002)

1,283.56 rating

Confidence interval: 1,275.18 – 1,291.95

5463 votes

Category
longer_query
Evaluated configuration
Gemini 1.5 Flash (002)
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-10-28 · rating

Gemini 1.5 Flash (002)

1,269.08 rating

Confidence interval: 1,260.46 – 1,277.70

4789 votes

Category
math
Evaluated configuration
Gemini 1.5 Flash (002)
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-10-28 · rating

Gemini 1.5 Flash (002)

1,252.60 rating

Confidence interval: 1,244.30 – 1,260.89

6324 votes

Category
multi_turn
Evaluated configuration
Gemini 1.5 Flash (002)
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-10-28 · rating

Gemini 1.5 Flash (002)

1,278.15 rating

Confidence interval: 1,272.51 – 1,283.79

16538 votes

Category
non_english
Evaluated configuration
Gemini 1.5 Flash (002)
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-10-28 · rating

Gemini 1.5 Flash (002)

1,286.63 rating

Confidence interval: 1,282.43 – 1,290.83

34902 votes

Category
overall
Evaluated configuration
Gemini 1.5 Flash (002)
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-10-28 · rating

Gemini 1.5 Flash (002)

1,287.31 rating

Confidence interval: 1,278.49 – 1,296.13

5101 votes

Category
russian
Evaluated configuration
Gemini 1.5 Flash (002)
Evaluation type
human preference
Arena text preference / spanishhuman preference · 2026-10-28 · rating

Gemini 1.5 Flash (002)

1,242.60 rating

Confidence interval: 1,208.91 – 1,276.28

283 votes

Category
spanish
Evaluated configuration
Gemini 1.5 Flash (002)
Evaluation type
human preference

Run it locally

Inference · memory estimate

Gemini 1.5 Flash (002)

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Model license
Proprietary