GeekRadar / The comparison desk
COMPARE.
AI models
amazon

Nova 2 Lite

AI model Released

Context window
1,000,000 tokens
Maximum output
65,536 tokens
Open weights
No

Capability & preference

Human preference · Arena

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

Nova 2 Lite 1361.8 nova-2-lite · 95% interval 1355.8–1367.8 · 12,413 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

Nova 2 Lite

1,364.43 rating

Confidence interval: 1,346.49 – 1,382.37

1080 votes

Category
chinese
Evaluated configuration
nova-2-lite
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating

Nova 2 Lite

1,385.32 rating

Confidence interval: 1,373.80 – 1,396.83

2580 votes

Category
coding
Evaluated configuration
nova-2-lite
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating

Nova 2 Lite

1,291.76 rating

Confidence interval: 1,277.32 – 1,306.19

1763 votes

Category
creative_writing
Evaluated configuration
nova-2-lite
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating

Nova 2 Lite

1,384.57 rating

Confidence interval: 1,376.04 – 1,393.09

5157 votes

Category
english
Evaluated configuration
nova-2-lite
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating

Nova 2 Lite

1,325.40 rating

Confidence interval: 1,316.87 – 1,333.93

8895 votes

Category
exclude_ties
Evaluated configuration
nova-2-lite
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-15 · rating

Nova 2 Lite

1,358.19 rating

Confidence interval: 1,337.61 – 1,378.78

789 votes

Category
expert
Evaluated configuration
nova-2-lite
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-10-15 · rating

Nova 2 Lite

1,380.57 rating

Confidence interval: 1,344.14 – 1,417.01

267 votes

Category
french
Evaluated configuration
nova-2-lite
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-15 · rating

Nova 2 Lite

1,342.92 rating

Confidence interval: 1,307.34 – 1,378.50

283 votes

Category
german
Evaluated configuration
nova-2-lite
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating

Nova 2 Lite

1,364.03 rating

Confidence interval: 1,356.27 – 1,371.79

6635 votes

Category
hard_prompts
Evaluated configuration
nova-2-lite
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating

Nova 2 Lite

1,385.25 rating

Confidence interval: 1,374.09 – 1,396.41

2748 votes

Category
hard_prompts_english
Evaluated configuration
nova-2-lite
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating

Nova 2 Lite

1,368.30 rating

Confidence interval: 1,356.02 – 1,380.57

2312 votes

Category
industry_business_and_management_and_financial_operations
Evaluated configuration
nova-2-lite
Evaluation type
human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating

Nova 2 Lite

1,308.58 rating

Confidence interval: 1,296.13 – 1,321.03

2252 votes

Category
industry_entertainment_and_sports_and_media
Evaluated configuration
nova-2-lite
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating

Nova 2 Lite

1,359.09 rating

Confidence interval: 1,339.22 – 1,378.97

900 votes

Category
industry_legal_and_government
Evaluated configuration
nova-2-lite
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating

Nova 2 Lite

1,382.30 rating

Confidence interval: 1,369.37 – 1,395.24

2131 votes

Category
industry_life_and_physical_and_social_science
Evaluated configuration
nova-2-lite
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating

Nova 2 Lite

1,368.53 rating

Confidence interval: 1,345.29 – 1,391.77

644 votes

Category
industry_mathematical
Evaluated configuration
nova-2-lite
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating

Nova 2 Lite

1,386.04 rating

Confidence interval: 1,364.45 – 1,407.62

746 votes

Category
industry_medicine_and_healthcare
Evaluated configuration
nova-2-lite
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating

Nova 2 Lite

1,394.42 rating

Confidence interval: 1,385.31 – 1,403.54

4306 votes

Category
industry_software_and_it_services
Evaluated configuration
nova-2-lite
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating

Nova 2 Lite

1,317.70 rating

Confidence interval: 1,306.42 – 1,328.98

2807 votes

Category
industry_writing_and_literature_and_language
Evaluated configuration
nova-2-lite
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating

Nova 2 Lite

1,334.86 rating

Confidence interval: 1,324.72 – 1,345.01

3421 votes

Category
instruction_following
Evaluated configuration
nova-2-lite
Evaluation type
human preference
Arena text preference / japanesehuman preference · 2026-10-15 · rating

Nova 2 Lite

1,273.22 rating

Confidence interval: 1,215.13 – 1,331.31

115 votes

Category
japanese
Evaluated configuration
nova-2-lite
Evaluation type
human preference
Arena text preference / koreanhuman preference · 2026-10-15 · rating

Nova 2 Lite

1,283.16 rating

Confidence interval: 1,235.01 – 1,331.31

160 votes

Category
korean
Evaluated configuration
nova-2-lite
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating

Nova 2 Lite

1,335.48 rating

Confidence interval: 1,324.85 – 1,346.12

3072 votes

Category
longer_query
Evaluated configuration
nova-2-lite
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating

Nova 2 Lite

1,358.69 rating

Confidence interval: 1,339.07 – 1,378.32

861 votes

Category
math
Evaluated configuration
nova-2-lite
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating

Nova 2 Lite

1,338.19 rating

Confidence interval: 1,325.07 – 1,351.31

2091 votes

Category
multi_turn
Evaluated configuration
nova-2-lite
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating

Nova 2 Lite

1,337.06 rating

Confidence interval: 1,329.56 – 1,344.57

7235 votes

Category
non_english
Evaluated configuration
nova-2-lite
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating

Nova 2 Lite

1,361.83 rating

Confidence interval: 1,355.82 – 1,367.83

12413 votes

Category
overall
Evaluated configuration
nova-2-lite
Evaluation type
human preference
Arena text preference / polishhuman preference · 2026-10-15 · rating

Nova 2 Lite

1,327.12 rating

Confidence interval: 1,297.51 – 1,356.73

421 votes

Category
polish
Evaluated configuration
nova-2-lite
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-10-15 · rating

Nova 2 Lite

1,342.17 rating

Confidence interval: 1,327.12 – 1,357.21

1448 votes

Category
russian
Evaluated configuration
nova-2-lite
Evaluation type
human preference
Arena text preference / spanishhuman preference · 2026-10-15 · rating

Nova 2 Lite

1,372.61 rating

Confidence interval: 1,333.32 – 1,411.89

232 votes

Category
spanish
Evaluated configuration
nova-2-lite
Evaluation type
human preference

Run it locally

Inference · memory estimate

Nova 2 Lite

Closed weights. No supported local deployment or GPU requirement is published.

API cost

USD / month

Standard text-token estimate. Excludes taxes, caching, batch discounts, reasoning and multimodal surcharges. Provider limits and regional availability may differ.

Nova 2 Lite

Capabilities

Context window
1,000,000 tokens
Maximum output
65,536 tokens
Reasoning
Yes
Tool calling
Yes
Open weights
No
Knowledge cutoff
2025-10
Model license
Proprietary

Input modalities

  • text
  • image
  • video
  • pdf

Output modalities

  • text