NVIDIA-Nemotron-Nano-9B-v2 model card (Hugging Face) Aug 18, 2025
- AIME25 72.1
- MATH500 97.8
- GPQA 64
- LCB (version not stated) 71.1
- BFCL v3 66.9
- IFEval (Instruction Strict) 90.3
- HLE 6.5
- RULER (128K) 78.9
nvidia-nemotron-nano-9b-v2
nvidia-nemotron-nano-9b-v2.
Released August 18th, 2025 Compare with others
14
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Unknown lab Aug 2025
nvidia-nemotron-nano-9b-v2
132.5
#257 of 404
Self-Reported Index, from the lab's own numbers. No Epoch Capabilities Index score yet.
- IFBench 34.6% #74 /80
- AgentIF (2026-10 setting) 61.2% #14 /24
- AIME 2025 72.1% #108 /143
Where it ranks
Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.
Knowledge and language
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| IFEval | 90.3% | #27 of 135 | Lab model card | |
| AgentIF (2026-10 setting) | 61.2% | #14 of 24 | Official leaderboard | |
| RULER | 78.9% | #34 of 42 | Lab model card | |
| IFBench | 34.6% | #74 of 80 | Lab model card | |
| BullshitBench V2 | 5.00% | #125 of 129 | Official leaderboard | |
| BullshitBench | 7.27% | #104 of 107 | Official leaderboard | |
| Humanity's Last Exam | 6.50% | #150 of 154 | Lab model card | |
| Fiction.LiveBench | 25% | #57 of 57 | Fiction.live leaderboard, via Epoch AI |
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| MATH-500 | 97.8% | #11 of 70 | Lab model card | |
| AIME 2024 | 81.9% | #34 of 88 | Lab model card | |
| GPQA Diamond | 64% | #211 of 302 | Lab model card | |
| AIME 2025 | 72.1% | #108 of 143 | Lab model card |
Coding
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| LiveCodeBench | 71.1% | #15 of 54 | Lab model card |
Agents and tools
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Berkeley Function Calling Leaderboard (BFCL) | 66.9% | #25 of 41 | Lab model card |
Its lab's numbers put it at 132.5, number 257 of 404
The Self-Reported Index fits one score to the 10 capability results the lab reported for this model, on the scale of the Epoch Capabilities Index. Labs choose which benchmarks to show and how to run them, so read it as the lab's claim, not an independent measurement. The 90% interval runs from 129.5 to 135.5. How we compute it.
- MATH-500 97.8
- IFEval 90.3
- AIME 2024 81.9
- RULER 78.9
- AIME 2025 72.1
- LiveCodeBench 71.1
- Berkeley Function Calling Leaderboard (BFCL) 66.9
- GPQA Diamond 64
- IFBench 34.6
- Humanity's Last Exam 6.5
Its launch post
The benchmarks the lab chose to headline, with the scores it gave.
Its system card
Every result in the longer documents the lab published with it. 2 of them aren't in the launch post.
NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model Aug 20, 2025
Capabilities
- IFBench 34.6
- AIME 2024 81.9
- AIME 2025 72
- GPQA Diamond 64
- LiveCodeBench
- Berkeley Function Calling Leaderboard (BFCL) 66.9
- RULER 78.9