Model comparison
Nemotron 3 Nano 30B A3B vs Sonar
Nemotron 3 Nano 30B A3B is the stronger model overall, scoring 39.9 to 37.8 on the Noometry Index.
Last verified . 0 shared benchmarks.
NVIDIA
PerplexitySummary
- The widest gap is in reasoning, where Nemotron 3 Nano 30B A3B leads 26.0 to 20.3.
- Nemotron 3 Nano 30B A3B is cheaper at $0.05 / $0.20 per million input/output tokens, against $1 / $1 for Sonar.
- Nemotron 3 Nano 30B A3B accepts more context: 262K tokens versus 128K.
- Nemotron 3 Nano 30B A3B has downloadable open weights; the other is API-only.
Side by side
| Nemotron 3 Nano 30B A3B | Sonar | |
|---|---|---|
| Provider | NVIDIA | Perplexity |
| Noometry Index | 39.9 | 37.8 |
| Released | 2025-12-15 | 2024-01-01 |
| Weights | Open | Proprietary |
| Context window | 262K | 128K |
| Max output | 262K | 4K |
| Input $ / M tokens | $0.05 | $1 |
| Output $ / M tokens | $0.20 | $1 |
| Results tracked | 18 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Nemotron 3 Nano 30B A3B leads
Nemotron 3 Nano 30B A3B: 39.9 (#139), Sonar: 35.1 (#217)
| Benchmark | Nemotron 3 Nano 30B A3B | Sonar |
|---|---|---|
| LiveBench Coding | — | 35.1% |
| LMArena Coding | 1378 | — |
Reasoning Nemotron 3 Nano 30B A3B leads
Nemotron 3 Nano 30B A3B: 26.0 (#123), Sonar: 20.3 (#221)
| Benchmark | Nemotron 3 Nano 30B A3B | Sonar |
|---|---|---|
| LiveBench Reasoning | — | 46.3% |
| LMArena Hard Prompts | 1348 | — |
| LiveBench Data Analysis | — | 37.9% |
| LiveBench | — | 46.9% |
Math Nemotron 3 Nano 30B A3B leads
Nemotron 3 Nano 30B A3B: 35.0 (#147), Sonar: 31.3 (#197)
| Benchmark | Nemotron 3 Nano 30B A3B | Sonar |
|---|---|---|
| LiveBench Math | — | 41.6% |
| LMArena Math | 1369 | — |
Knowledge Not comparable
Nemotron 3 Nano 30B A3B: 37.6 (#145), Sonar: —
| Benchmark | Nemotron 3 Nano 30B A3B | Sonar |
|---|---|---|
| Vectara Hallucination Rate | 9.6% | — |
| LMArena Expert | 1354 | — |
Multilingual Not comparable
Nemotron 3 Nano 30B A3B: 46.0 (#158), Sonar: —
| Benchmark | Nemotron 3 Nano 30B A3B | Sonar |
|---|---|---|
| LMArena Non-English | 1320 | — |
| LMArena Chinese | 1382 | — |
| LMArena French | 1396 | — |
| LMArena German | 1349 | — |
| LMArena Japanese | 1270 | — |
| LMArena Korean | 1269 | — |
| LMArena Russian | 1303 | — |
| LMArena Spanish | 1377 | — |
Instruction Following Sonar leads
Nemotron 3 Nano 30B A3B: 69.0 (#175), Sonar: 71.5 (#146)
| Benchmark | Nemotron 3 Nano 30B A3B | Sonar |
|---|---|---|
| LiveBench Instruction Following | — | 76.2% |
| LMArena Instruction Following | 1303 | — |
Long Context Not comparable
Nemotron 3 Nano 30B A3B: 39.5 (#170), Sonar: —
| Benchmark | Nemotron 3 Nano 30B A3B | Sonar |
|---|---|---|
| LMArena Longer Query | 1300 | — |
Writing & Preference Too close to call
Nemotron 3 Nano 30B A3B: 52.5 (#169), Sonar: 52.6 (#166)
| Benchmark | Nemotron 3 Nano 30B A3B | Sonar |
|---|---|---|
| LMArena Text | 1348 | — |
| LMArena Creative Writing | 1269 | — |
| LMArena Multi-Turn | 1319 | — |
| LiveBench Language | — | 44.1% |
Frequently asked questions
Is Nemotron 3 Nano 30B A3B better than Sonar?
Nemotron 3 Nano 30B A3B is the stronger model overall, scoring 39.9 to 37.8 on the Noometry Index.
Which is cheaper, Nemotron 3 Nano 30B A3B or Sonar?
Nemotron 3 Nano 30B A3B is cheaper. It lists at $0.05 per million input tokens and $0.20 per million output tokens; Sonar lists at $1 and $1.
Is Nemotron 3 Nano 30B A3B or Sonar better for coding?
Nemotron 3 Nano 30B A3B scores higher on coding benchmarks: 39.9 versus 35.1 in the Noometry coding category.
Which has the bigger context window?
Nemotron 3 Nano 30B A3B does, with 262K tokens against 128K.
How many benchmarks do Nemotron 3 Nano 30B A3B and Sonar share?
0 benchmarks have published results for both models. Nemotron 3 Nano 30B A3B has 18 scored results on Noometry and Sonar has 7.