
NVIDIA-Nemotron-3-Super-120B-A12B
NVIDIA-Nemotron-3-Super-120B-A12B is an open-weight model from NVIDIA. It ranks #177 of 351 on the LMArena text leaderboard with a rating of 1378.
- Developer
- NVIDIA
- Released
- Mar 6, 2026
- Context window
- —
- Price in / out, per 1M tokens
- —
- Weights
- Open · NVIDIA Open Model
- Inputs
- —
- Reasoning
- —
- Tool use
- —
The rating LMArena published at each update since Mar 6, 2026. Ratings move as votes come in and new models join.
LMArena, by category
| Leaderboard | Rating | Rank | Votes |
|---|---|---|---|
| TextLMArena | 1378 | 177 / 351 | 7.9K |
| CodingLMArena | 1404 | 172 / 346 | 1.9K |
| MathLMArena | 1380 | 184 / 339 | 547 |
| Creative writingLMArena | 1317 | 207 / 349 | 1.1K |
| Instruction followingLMArena | 1347 | 191 / 351 | 2.2K |
| Hard promptsLMArena | 1386 | 174 / 351 | 4.4K |
| Multi-turnLMArena | 1369 | 183 / 349 | 1.4K |
| Long queriesLMArena | 1362 | 188 / 330 | 2.3K |
| ExpertLMArena | 1398 | 161 / 305 | 656 |
| Legal and governmentIndustries | 1392 | 168 / 325 | 552 |
| Medicine and healthcareIndustries | 1383 | 179 / 325 | 512 |
| Business and financeIndustries | 1364 | 181 / 344 | 1.5K |
| ChineseLanguages | 1432 | 150 / 328 | 584 |
| SpanishLanguages | 1418 | 120 / 249 | 352 |
| GermanLanguages | 1341 | 179 / 261 | 200 |
| FrenchLanguages | 1403 | 153 / 252 | 279 |
LMArena, CC BY 4.0, as of Oct 22, 2026. Where a model is rated at several effort levels, its best is shown.
Compare NVIDIA-Nemotron-3-Super-120B-A12B
NVIDIA
The GPU maker also publishes Nemotron, open models tuned for enterprise and reasoning. Founded 1993, based in Santa Clara. nvidia.com
Questions
Who makes NVIDIA-Nemotron-3-Super-120B-A12B?
NVIDIA-Nemotron-3-Super-120B-A12B is made by NVIDIA, founded 1993 and based in Santa Clara.
How does NVIDIA-Nemotron-3-Super-120B-A12B rank?
#177 of 351 on LMArena’s text leaderboard, rated 1378 (95% interval 1371–1385) from 7,869 votes, as of Oct 22, 2026.
Is NVIDIA-Nemotron-3-Super-120B-A12B open source?
NVIDIA-Nemotron-3-Super-120B-A12B has open weights under the NVIDIA Open Model license.
Gemini 4 Argon
Claude Opus 5.5
Muse Wonder
MiMo-V2.6-Pro
Qwen3.8-Max
Kimi K3
GLM-5.3
GPT-5.5
ERNIE 5.1
DeepSeek-V4.1-Flash-20260910
Grok 4.20 Beta
amazon-nova-experimental-chat
Dola Seed 2.0 Pro
Gemma 4 31B
Step 5 Preview