NVIDIA-Nemotron-3-Super-120B-A12B-BF16
NVIDIA- Arena score
- 1377
- Among open models
- #55of 148
- Among all on Arena
- #182
- Votes
- 7,842
Measured on NVIDIA-Nemotron-3-Super-120B-A12B, the served version, not a local build. LMArena, CC BY 4.0, published Nov 11, 2026.
Score by category
CategoryScoreOpen rankArena rankVotes
- Chinese1432#49#152583
- Spanish1417#38#124353
- Software & IT1409#53#1712.8K
- Applied math1405#51#163443
- Coding1404#54#1751.9K
- English1400#51#1693.1K
- French1399#46#155277
- Expert1399#50#162657
- Hard prompts, English1396#53#1761.8K
- Legal & government1391#51#172551
- Science1388#55#1771.2K
- Hard prompts1386#54#1774.4K
- Medicine & health1382#58#183507
- Math1379#57#184544
- Multi-turn1368#57#1871.4K
- Business & finance1364#56#1841.5K
- Long prompts1362#57#1912.3K
- Non-English1355#58#1904.7K
- Instructions1347#60#1942.2K
- Polish1347#50#177275
- Excluding ties1345#58#1855.4K
- German1341#55#183200
- Russian1336#66#2071K
- Media & sports1335#57#1881.3K
- Writing & literature1331#64#2061.7K
- Creative writing1315#65#2131.1K
About as strong, smaller
Compare
gemma-4-26B-A4B-itGoogle143425.8B

Qwen3.8-27BQwen143727.8B

Qwen3.5-27BQwen140927.8B

Muse-Glimmer-30Bmeta-models138929.8B
Built on it
Ways to run it
- GGUF · llama.cpp, Ollama, LM Studiounsloth/NVIDIA-Nemotron-3-Super-120B-A12B-GGUF25 builds
- MLX · Apple silicon: mlx-lm, LM Studiomlx-community/NVIDIA-Nemotron-3-Super-120B-A12B-4bit21 builds
Most downloaded
- NVIDIA-Nemotron-Labs-3-Puzzle-75B-A9B-NVFP4nvidia · Quantization51.8K downloads
- NVIDIA-Nemotron-3-Super-120B-A12B-GGUFunsloth · Quantization10.1K downloads
- nvidia_Nemotron-3-Super-120B-A12B-GGUFbartowski · Quantization3K downloads
- NVIDIA-Nemotron-3-Super-120B-A12B-GGUFlmstudio-community · Quantization2.6K downloads
- NVIDIA-Nemotron-3-Super-120B-A12B-APEX-GGUFmudler · Quantization2.5K downloads
BenchClub runs
Not runnable yet
Runs open once a NVIDIA-Nemotron-3-Super-120B-A12B-BF16 build is registered.
More from NVIDIA
See moreOther 80–300B models
See more
DeepSeek-V4-FlashDeepSeek1.2M291B

MiniMax-M2.5MiniMax1M229B
Inkling-SmallThinking Machines1M266B
Hy3Tencent987.2K299B