GeekRadar / The comparison desk
COMPARE.
AI models
nvidia

Llama 3.1 Nemotron Ultra 253B v1

Model evaluation

Capability & preference

Human preference · Arena

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

Llama 3.1 Nemotron Ultra 253B v1 1319.6 Llama 3.1 Nemotron Ultra 253B v1 · 95% interval 1308.1–1331.1 · 2,549 votes · 2026-11-11

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 / codinghuman preference · 2026-11-11 · rating

Llama 3.1 Nemotron Ultra 253B v1

1,311.71 rating

Confidence interval: 1,282.22 – 1,341.20

367 votes

Category
coding
Evaluated configuration
Llama 3.1 Nemotron Ultra 253B v1
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-11-11 · rating

Llama 3.1 Nemotron Ultra 253B v1

1,314.13 rating

Confidence interval: 1,287.74 – 1,340.52

444 votes

Category
creative_writing
Evaluated configuration
Llama 3.1 Nemotron Ultra 253B v1
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-11-11 · rating

Llama 3.1 Nemotron Ultra 253B v1

1,345.06 rating

Confidence interval: 1,330.38 – 1,359.73

1491 votes

Category
english
Evaluated configuration
Llama 3.1 Nemotron Ultra 253B v1
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-11-11 · rating

Llama 3.1 Nemotron Ultra 253B v1

1,263.47 rating

Confidence interval: 1,246.29 – 1,280.65

1699 votes

Category
exclude_ties
Evaluated configuration
Llama 3.1 Nemotron Ultra 253B v1
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-11-11 · rating

Llama 3.1 Nemotron Ultra 253B v1

1,315.96 rating

Confidence interval: 1,295.07 – 1,336.86

713 votes

Category
hard_prompts
Evaluated configuration
Llama 3.1 Nemotron Ultra 253B v1
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-11-11 · rating

Llama 3.1 Nemotron Ultra 253B v1

1,336.21 rating

Confidence interval: 1,309.94 – 1,362.48

448 votes

Category
hard_prompts_english
Evaluated configuration
Llama 3.1 Nemotron Ultra 253B v1
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-11-11 · rating

Llama 3.1 Nemotron Ultra 253B v1

1,301.14 rating

Confidence interval: 1,267.40 – 1,334.87

254 votes

Category
industry_business_and_management_and_financial_operations
Evaluated configuration
Llama 3.1 Nemotron Ultra 253B v1
Evaluation type
human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-11-11 · rating

Llama 3.1 Nemotron Ultra 253B v1

1,276.22 rating

Confidence interval: 1,252.98 – 1,299.45

532 votes

Category
industry_entertainment_and_sports_and_media
Evaluated configuration
Llama 3.1 Nemotron Ultra 253B v1
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-11-11 · rating

Llama 3.1 Nemotron Ultra 253B v1

1,324.07 rating

Confidence interval: 1,298.44 – 1,349.70

498 votes

Category
industry_life_and_physical_and_social_science
Evaluated configuration
Llama 3.1 Nemotron Ultra 253B v1
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-11-11 · rating

Llama 3.1 Nemotron Ultra 253B v1

1,326.61 rating

Confidence interval: 1,303.26 – 1,349.96

588 votes

Category
industry_software_and_it_services
Evaluated configuration
Llama 3.1 Nemotron Ultra 253B v1
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-11-11 · rating

Llama 3.1 Nemotron Ultra 253B v1

1,300.17 rating

Confidence interval: 1,279.34 – 1,321.01

712 votes

Category
industry_writing_and_literature_and_language
Evaluated configuration
Llama 3.1 Nemotron Ultra 253B v1
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-11-11 · rating

Llama 3.1 Nemotron Ultra 253B v1

1,307.60 rating

Confidence interval: 1,286.52 – 1,328.67

660 votes

Category
instruction_following
Evaluated configuration
Llama 3.1 Nemotron Ultra 253B v1
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-11-11 · rating

Llama 3.1 Nemotron Ultra 253B v1

1,298.67 rating

Confidence interval: 1,269.09 – 1,328.24

321 votes

Category
longer_query
Evaluated configuration
Llama 3.1 Nemotron Ultra 253B v1
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-11-11 · rating

Llama 3.1 Nemotron Ultra 253B v1

1,359.63 rating

Confidence interval: 1,322.62 – 1,396.63

209 votes

Category
math
Evaluated configuration
Llama 3.1 Nemotron Ultra 253B v1
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-11-11 · rating

Llama 3.1 Nemotron Ultra 253B v1

1,317.23 rating

Confidence interval: 1,287.35 – 1,347.11

374 votes

Category
multi_turn
Evaluated configuration
Llama 3.1 Nemotron Ultra 253B v1
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-11-11 · rating

Llama 3.1 Nemotron Ultra 253B v1

1,282.22 rating

Confidence interval: 1,265.29 – 1,299.15

1058 votes

Category
non_english
Evaluated configuration
Llama 3.1 Nemotron Ultra 253B v1
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-11-11 · rating

Llama 3.1 Nemotron Ultra 253B v1

1,319.57 rating

Confidence interval: 1,308.06 – 1,331.09

2549 votes

Category
overall
Evaluated configuration
Llama 3.1 Nemotron Ultra 253B v1
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-11-11 · rating

Llama 3.1 Nemotron Ultra 253B v1

1,283.66 rating

Confidence interval: 1,254.25 – 1,313.07

303 votes

Category
russian
Evaluated configuration
Llama 3.1 Nemotron Ultra 253B v1
Evaluation type
human preference

Run it locally

Inference · memory estimate

Llama 3.1 Nemotron Ultra 253B v1

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Model license
Nvidia Open Model