Model comparison
Llama 3.1 Nemotron Ultra 253b v1 vs Nemotron 3 Nano 30B A3B
Nemotron 3 Nano 30B A3B is the stronger model overall, scoring 40.6 to 36.7 on the Noometry Index.
Last verified . 10 shared benchmarks.
NVIDIASummary
- They share 10 benchmarks with published results for both. Llama 3.1 Nemotron Ultra 253b v1 scores higher in 1 category and Nemotron 3 Nano 30B A3B in 6 categories; 2 gaps are clear of the uncertainty.
Side by side
| Llama 3.1 Nemotron Ultra 253b v1 | Nemotron 3 Nano 30B A3B | |
|---|---|---|
| Provider | NVIDIA | NVIDIA |
| Noometry Index | 36.7 | 40.6 |
| Released | — | 2025-12-15 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 262K |
| Input $ / M tokens | — | $0.05 |
| Output $ / M tokens | — | $0.20 |
| Results tracked | 11 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Nemotron 3 Nano 30B A3B leads
Llama 3.1 Nemotron Ultra 253b v1: 38.4 (#177), Nemotron 3 Nano 30B A3B: 40.5 (#138)
| Benchmark | Llama 3.1 Nemotron Ultra 253b v1 | Nemotron 3 Nano 30B A3B |
|---|---|---|
| LMArena Coding | 1312 | 1378 |
Agentic & Tool Use Not comparable
Llama 3.1 Nemotron Ultra 253b v1: 15.7 (#149), Nemotron 3 Nano 30B A3B: —
| Benchmark | Llama 3.1 Nemotron Ultra 253b v1 | Nemotron 3 Nano 30B A3B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 10% | — |
Reasoning Too close to call
Llama 3.1 Nemotron Ultra 253b v1: 26.3 (#134), Nemotron 3 Nano 30B A3B: 27.1 (#124)
| Benchmark | Llama 3.1 Nemotron Ultra 253b v1 | Nemotron 3 Nano 30B A3B |
|---|---|---|
| LMArena Hard Prompts | 1316 | 1348 |
Math Too close to call
Llama 3.1 Nemotron Ultra 253b v1: 37.5 (#152), Nemotron 3 Nano 30B A3B: 37.8 (#147)
| Benchmark | Llama 3.1 Nemotron Ultra 253b v1 | Nemotron 3 Nano 30B A3B |
|---|---|---|
| LMArena Math | 1360 | 1371 |
Knowledge Not comparable
Llama 3.1 Nemotron Ultra 253b v1: —, Nemotron 3 Nano 30B A3B: 38.2 (#148)
| Benchmark | Llama 3.1 Nemotron Ultra 253b v1 | Nemotron 3 Nano 30B A3B |
|---|---|---|
| Vectara Hallucination Rate | — | 9.6% |
| LMArena Expert | — | 1355 |
Multilingual Nemotron 3 Nano 30B A3B leads
Llama 3.1 Nemotron Ultra 253b v1: 43.1 (#187), Nemotron 3 Nano 30B A3B: 45.8 (#162)
| Benchmark | Llama 3.1 Nemotron Ultra 253b v1 | Nemotron 3 Nano 30B A3B |
|---|---|---|
| LMArena Non-English | 1282 | 1320 |
| LMArena Russian | 1284 | 1303 |
| LMArena Chinese | — | 1382 |
| LMArena French | — | 1396 |
| LMArena German | — | 1348 |
| LMArena Japanese | — | 1268 |
| LMArena Korean | — | 1269 |
| LMArena Spanish | — | 1376 |
Instruction Following Too close to call
Llama 3.1 Nemotron Ultra 253b v1: 69.0 (#178), Nemotron 3 Nano 30B A3B: 68.8 (#180)
| Benchmark | Llama 3.1 Nemotron Ultra 253b v1 | Nemotron 3 Nano 30B A3B |
|---|---|---|
| LMArena Instruction Following | 1308 | 1304 |
Long Context Too close to call
Llama 3.1 Nemotron Ultra 253b v1: 39.5 (#177), Nemotron 3 Nano 30B A3B: 39.5 (#175)
| Benchmark | Llama 3.1 Nemotron Ultra 253b v1 | Nemotron 3 Nano 30B A3B |
|---|---|---|
| LMArena Longer Query | 1299 | 1300 |
Writing & Preference Too close to call
Llama 3.1 Nemotron Ultra 253b v1: 52.2 (#175), Nemotron 3 Nano 30B A3B: 52.3 (#174)
| Benchmark | Llama 3.1 Nemotron Ultra 253b v1 | Nemotron 3 Nano 30B A3B |
|---|---|---|
| LMArena Text | 1320 | 1348 |
| LMArena Creative Writing | 1314 | 1269 |
| LMArena Multi-Turn | 1317 | 1319 |
Frequently asked questions
Is Llama 3.1 Nemotron Ultra 253b v1 better than Nemotron 3 Nano 30B A3B?
Nemotron 3 Nano 30B A3B is the stronger model overall, scoring 40.6 to 36.7 on the Noometry Index.
Is Llama 3.1 Nemotron Ultra 253b v1 or Nemotron 3 Nano 30B A3B better for coding?
Nemotron 3 Nano 30B A3B scores higher on coding benchmarks: 40.5 versus 38.4 in the Noometry coding category.
How many benchmarks do Llama 3.1 Nemotron Ultra 253b v1 and Nemotron 3 Nano 30B A3B share?
10 benchmarks have published results for both models. Llama 3.1 Nemotron Ultra 253b v1 has 11 scored results on Noometry and Nemotron 3 Nano 30B A3B has 18.