Llama 3.3 Nemotron Super 49B v1
Stored tensors can include buffers and repeated shared weights. A verified unique parameter count is unavailable. Checkpoint size is not the memory required to run the model.
GeekRadar / The comparison desk
COMPARE.
AI modelsLlama 3.3 Nemotron Super 49B v1
AI model Released
- Context window
- 131,072 tokens
- Maximum output
- 131,072 tokens
- Open weights
- Yes
Capability & preference
Human preference · Arena
Overall text preferences from head-to-head votes. Not factual accuracy or a task-success rate.
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 · 2026-11-09 · rating
Llama 3.3 Nemotron Super 49B v1
1,276.83 rating
Confidence interval: 1,237.88 – 1,315.77
211 votes
- Category
- chinese
- Evaluated configuration
- Llama 3.3 Nemotron Super 49B v1
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-11-09 · rating
Llama 3.3 Nemotron Super 49B v1
1,295.48 rating
Confidence interval: 1,264.94 – 1,326.03
286 votes
- Category
- coding
- Evaluated configuration
- Llama 3.3 Nemotron Super 49B v1
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-11-09 · rating
Llama 3.3 Nemotron Super 49B v1
1,287.91 rating
Confidence interval: 1,261.05 – 1,314.78
428 votes
- Category
- creative_writing
- Evaluated configuration
- Llama 3.3 Nemotron Super 49B v1
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-11-09 · rating
Llama 3.3 Nemotron Super 49B v1
1,353.80 rating
Confidence interval: 1,338.29 – 1,369.30
1250 votes
- Category
- english
- Evaluated configuration
- Llama 3.3 Nemotron Super 49B v1
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-11-09 · rating
Llama 3.3 Nemotron Super 49B v1
1,251.70 rating
Confidence interval: 1,232.89 – 1,270.51
1430 votes
- Category
- exclude_ties
- Evaluated configuration
- Llama 3.3 Nemotron Super 49B v1
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-11-09 · rating
Llama 3.3 Nemotron Super 49B v1
1,311.11 rating
Confidence interval: 1,287.34 – 1,334.88
510 votes
- Category
- hard_prompts
- Evaluated configuration
- Llama 3.3 Nemotron Super 49B v1
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-11-09 · rating
Llama 3.3 Nemotron Super 49B v1
1,337.61 rating
Confidence interval: 1,308.90 – 1,366.31
344 votes
- Category
- hard_prompts_english
- Evaluated configuration
- Llama 3.3 Nemotron Super 49B v1
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-11-09 · rating
Llama 3.3 Nemotron Super 49B v1
1,286.29 rating
Confidence interval: 1,252.09 – 1,320.50
241 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- Llama 3.3 Nemotron Super 49B v1
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-11-09 · rating
Llama 3.3 Nemotron Super 49B v1
1,288.98 rating
Confidence interval: 1,262.28 – 1,315.67
410 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- Llama 3.3 Nemotron Super 49B v1
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-11-09 · rating
Llama 3.3 Nemotron Super 49B v1
1,332.53 rating
Confidence interval: 1,304.63 – 1,360.43
395 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- Llama 3.3 Nemotron Super 49B v1
- Evaluation type
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-11-09 · rating
Llama 3.3 Nemotron Super 49B v1
1,344.20 rating
Confidence interval: 1,307.58 – 1,380.83
207 votes
- Category
- industry_mathematical
- Evaluated configuration
- Llama 3.3 Nemotron Super 49B v1
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-11-09 · rating
Llama 3.3 Nemotron Super 49B v1
1,300.41 rating
Confidence interval: 1,276.45 – 1,324.37
493 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- Llama 3.3 Nemotron Super 49B v1
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-11-09 · rating
Llama 3.3 Nemotron Super 49B v1
1,300.48 rating
Confidence interval: 1,277.94 – 1,323.01
614 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- Llama 3.3 Nemotron Super 49B v1
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-11-09 · rating
Llama 3.3 Nemotron Super 49B v1
1,293.27 rating
Confidence interval: 1,273.87 – 1,312.67
803 votes
- Category
- instruction_following
- Evaluated configuration
- Llama 3.3 Nemotron Super 49B v1
- Evaluation type
- human preference
Arena text preference / longer_queryhuman preference · 2026-11-09 · rating
Llama 3.3 Nemotron Super 49B v1
1,299.25 rating
Confidence interval: 1,269.35 – 1,329.15
317 votes
- Category
- longer_query
- Evaluated configuration
- Llama 3.3 Nemotron Super 49B v1
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-11-09 · rating
Llama 3.3 Nemotron Super 49B v1
1,314.97 rating
Confidence interval: 1,283.32 – 1,346.62
301 votes
- Category
- multi_turn
- Evaluated configuration
- Llama 3.3 Nemotron Super 49B v1
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-11-09 · rating
Llama 3.3 Nemotron Super 49B v1
1,253.38 rating
Confidence interval: 1,235.55 – 1,271.20
968 votes
- Category
- non_english
- Evaluated configuration
- Llama 3.3 Nemotron Super 49B v1
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-11-09 · rating
Llama 3.3 Nemotron Super 49B v1
1,308.39 rating
Confidence interval: 1,296.35 – 1,320.44
2218 votes
- Category
- overall
- Evaluated configuration
- Llama 3.3 Nemotron Super 49B v1
- Evaluation type
- human preference
Arena text preference / russianhuman preference · 2026-11-09 · rating
Llama 3.3 Nemotron Super 49B v1
1,269.22 rating
Confidence interval: 1,234.75 – 1,303.68
263 votes
- Category
- russian
- Evaluated configuration
- Llama 3.3 Nemotron Super 49B v1
- Evaluation type
- human preference
Run it locally
API cost
Standard text-token estimate. Excludes taxes, caching, batch discounts, reasoning and multimodal surcharges. Provider limits and regional availability may differ.
Llama 3.3 Nemotron Super 49B v1
Capabilities
- Context window
- 131,072 tokens
- Maximum output
- 131,072 tokens
- Reasoning
- Yes
- Tool calling
- Yes
- Open weights
- Yes
- Checkpoint tensor payload
- 92.88 GiB
Input modalities
- text
Output modalities
- text
Processing & platform
- Architecture
- nemotron-nas
0 selected Compare 0