GeekRadar / The comparison desk
COMPARE.
AI models
nvidia

nvidia-llama-3.3-nemotron-super-49b-v1.5

Model evaluation

Capability & preference

Human preference · Arena

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

nvidia-llama-3.3-nemotron-super-49b-v1.5 1338.0 nvidia-llama-3.3-nemotron-super-49b-v1.5 · 95% interval 1328.1–1348.0 · 3,328 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 / codinghuman preference · 2026-10-15 · rating

nvidia-llama-3.3-nemotron-super-49b-v1.5

1,355.30 rating

Confidence interval: 1,333.40 – 1,377.19

653 votes

Category
coding
Evaluated configuration
nvidia-llama-3.3-nemotron-super-49b-v1.5
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating

nvidia-llama-3.3-nemotron-super-49b-v1.5

1,306.63 rating

Confidence interval: 1,277.58 – 1,335.67

370 votes

Category
creative_writing
Evaluated configuration
nvidia-llama-3.3-nemotron-super-49b-v1.5
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating

nvidia-llama-3.3-nemotron-super-49b-v1.5

1,358.95 rating

Confidence interval: 1,343.92 – 1,373.98

1390 votes

Category
english
Evaluated configuration
nvidia-llama-3.3-nemotron-super-49b-v1.5
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating

nvidia-llama-3.3-nemotron-super-49b-v1.5

1,292.55 rating

Confidence interval: 1,277.95 – 1,307.16

2271 votes

Category
exclude_ties
Evaluated configuration
nvidia-llama-3.3-nemotron-super-49b-v1.5
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-15 · rating

nvidia-llama-3.3-nemotron-super-49b-v1.5

1,329.60 rating

Confidence interval: 1,288.84 – 1,370.36

180 votes

Category
expert
Evaluated configuration
nvidia-llama-3.3-nemotron-super-49b-v1.5
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating

nvidia-llama-3.3-nemotron-super-49b-v1.5

1,335.47 rating

Confidence interval: 1,320.50 – 1,350.44

1436 votes

Category
hard_prompts
Evaluated configuration
nvidia-llama-3.3-nemotron-super-49b-v1.5
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating

nvidia-llama-3.3-nemotron-super-49b-v1.5

1,343.34 rating

Confidence interval: 1,320.79 – 1,365.89

614 votes

Category
hard_prompts_english
Evaluated configuration
nvidia-llama-3.3-nemotron-super-49b-v1.5
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating

nvidia-llama-3.3-nemotron-super-49b-v1.5

1,311.09 rating

Confidence interval: 1,288.11 – 1,334.06

595 votes

Category
industry_business_and_management_and_financial_operations
Evaluated configuration
nvidia-llama-3.3-nemotron-super-49b-v1.5
Evaluation type
human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating

nvidia-llama-3.3-nemotron-super-49b-v1.5

1,282.78 rating

Confidence interval: 1,259.85 – 1,305.71

567 votes

Category
industry_entertainment_and_sports_and_media
Evaluated configuration
nvidia-llama-3.3-nemotron-super-49b-v1.5
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating

nvidia-llama-3.3-nemotron-super-49b-v1.5

1,348.90 rating

Confidence interval: 1,311.46 – 1,386.34

233 votes

Category
industry_legal_and_government
Evaluated configuration
nvidia-llama-3.3-nemotron-super-49b-v1.5
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating

nvidia-llama-3.3-nemotron-super-49b-v1.5

1,366.76 rating

Confidence interval: 1,343.71 – 1,389.81

594 votes

Category
industry_life_and_physical_and_social_science
Evaluated configuration
nvidia-llama-3.3-nemotron-super-49b-v1.5
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating

nvidia-llama-3.3-nemotron-super-49b-v1.5

1,397.57 rating

Confidence interval: 1,357.86 – 1,437.28

182 votes

Category
industry_mathematical
Evaluated configuration
nvidia-llama-3.3-nemotron-super-49b-v1.5
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating

nvidia-llama-3.3-nemotron-super-49b-v1.5

1,367.23 rating

Confidence interval: 1,326.17 – 1,408.29

195 votes

Category
industry_medicine_and_healthcare
Evaluated configuration
nvidia-llama-3.3-nemotron-super-49b-v1.5
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating

nvidia-llama-3.3-nemotron-super-49b-v1.5

1,359.22 rating

Confidence interval: 1,342.64 – 1,375.80

1180 votes

Category
industry_software_and_it_services
Evaluated configuration
nvidia-llama-3.3-nemotron-super-49b-v1.5
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating

nvidia-llama-3.3-nemotron-super-49b-v1.5

1,293.38 rating

Confidence interval: 1,271.49 – 1,315.27

665 votes

Category
industry_writing_and_literature_and_language
Evaluated configuration
nvidia-llama-3.3-nemotron-super-49b-v1.5
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating

nvidia-llama-3.3-nemotron-super-49b-v1.5

1,298.67 rating

Confidence interval: 1,278.90 – 1,318.44

807 votes

Category
instruction_following
Evaluated configuration
nvidia-llama-3.3-nemotron-super-49b-v1.5
Evaluation type
human preference
Arena text preference / japanesehuman preference · 2026-10-15 · rating

nvidia-llama-3.3-nemotron-super-49b-v1.5

1,300.36 rating

Confidence interval: 1,270.71 – 1,330.01

418 votes

Category
japanese
Evaluated configuration
nvidia-llama-3.3-nemotron-super-49b-v1.5
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating

nvidia-llama-3.3-nemotron-super-49b-v1.5

1,314.98 rating

Confidence interval: 1,293.50 – 1,336.46

653 votes

Category
longer_query
Evaluated configuration
nvidia-llama-3.3-nemotron-super-49b-v1.5
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating

nvidia-llama-3.3-nemotron-super-49b-v1.5

1,392.32 rating

Confidence interval: 1,353.73 – 1,430.90

194 votes

Category
math
Evaluated configuration
nvidia-llama-3.3-nemotron-super-49b-v1.5
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating

nvidia-llama-3.3-nemotron-super-49b-v1.5

1,333.49 rating

Confidence interval: 1,309.46 – 1,357.53

560 votes

Category
multi_turn
Evaluated configuration
nvidia-llama-3.3-nemotron-super-49b-v1.5
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating

nvidia-llama-3.3-nemotron-super-49b-v1.5

1,315.48 rating

Confidence interval: 1,302.57 – 1,328.39

1938 votes

Category
non_english
Evaluated configuration
nvidia-llama-3.3-nemotron-super-49b-v1.5
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating

nvidia-llama-3.3-nemotron-super-49b-v1.5

1,338.05 rating

Confidence interval: 1,328.06 – 1,348.03

3328 votes

Category
overall
Evaluated configuration
nvidia-llama-3.3-nemotron-super-49b-v1.5
Evaluation type
human preference
Arena text preference / polishhuman preference · 2026-10-15 · rating

nvidia-llama-3.3-nemotron-super-49b-v1.5

1,322.03 rating

Confidence interval: 1,293.16 – 1,350.91

398 votes

Category
polish
Evaluated configuration
nvidia-llama-3.3-nemotron-super-49b-v1.5
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-10-15 · rating

nvidia-llama-3.3-nemotron-super-49b-v1.5

1,332.06 rating

Confidence interval: 1,296.56 – 1,367.56

202 votes

Category
russian
Evaluated configuration
nvidia-llama-3.3-nemotron-super-49b-v1.5
Evaluation type
human preference

Run it locally

Inference · memory estimate

nvidia-llama-3.3-nemotron-super-49b-v1.5

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Model license
Nvidia Open