Model comparison
Nemotron 3.5 Lightning vs Sonar
Nemotron 3.5 Lightning is the stronger model overall, scoring 40.0 to 38.5 on the Noometry Index.
Last verified . 0 shared benchmarks.
NVIDIA
PerplexitySummary
- The widest gap is in reasoning, where Nemotron 3.5 Lightning leads 26.8 to 21.1.
- Nemotron 3.5 Lightning is cheaper at $0.05 / $0.20 per million input/output tokens, against $1 / $1 for Sonar.
- Nemotron 3.5 Lightning accepts more context: 262K tokens versus 128K.
- Nemotron 3.5 Lightning has downloadable open weights; the other is API-only.
Side by side
| Nemotron 3.5 Lightning | Sonar | |
|---|---|---|
| Provider | NVIDIA | Perplexity |
| Noometry Index | 40.0 | 38.5 |
| Released | 2026-08-11 | 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 3.5 Lightning leads
Nemotron 3.5 Lightning: 40.4 (#141), Sonar: 35.7 (#221)
| Benchmark | Nemotron 3.5 Lightning | Sonar |
|---|---|---|
| LiveBench Coding | — | 35.1% |
| LMArena Coding | 1375 | — |
Reasoning Nemotron 3.5 Lightning leads
Nemotron 3.5 Lightning: 26.8 (#127), Sonar: 21.1 (#227)
| Benchmark | Nemotron 3.5 Lightning | Sonar |
|---|---|---|
| LiveBench Reasoning | — | 46.3% |
| LMArena Hard Prompts | 1337 | — |
| LiveBench Data Analysis | — | 37.9% |
| LiveBench | — | 46.9% |
Math Nemotron 3.5 Lightning leads
Nemotron 3.5 Lightning: 37.5 (#155), Sonar: 33.7 (#200)
| Benchmark | Nemotron 3.5 Lightning | Sonar |
|---|---|---|
| LiveBench Math | — | 41.6% |
| LMArena Math | 1359 | — |
Knowledge Not comparable
Nemotron 3.5 Lightning: 37.5 (#154), Sonar: —
| Benchmark | Nemotron 3.5 Lightning | Sonar |
|---|---|---|
| LMArena Expert | 1356 | — |
Multilingual Not comparable
Nemotron 3.5 Lightning: 44.0 (#180), Sonar: —
| Benchmark | Nemotron 3.5 Lightning | Sonar |
|---|---|---|
| LMArena Non-English | 1295 | — |
| LMArena Chinese | 1359 | — |
| LMArena French | 1366 | — |
| LMArena German | 1282 | — |
| LMArena Japanese | 1206 | — |
| LMArena Korean | 1238 | — |
| LMArena Russian | 1253 | — |
| LMArena Spanish | 1345 | — |
Instruction Following Sonar leads
Nemotron 3.5 Lightning: 69.6 (#170), Sonar: 71.4 (#150)
| Benchmark | Nemotron 3.5 Lightning | Sonar |
|---|---|---|
| LiveBench Instruction Following | — | 76.2% |
| LMArena Instruction Following | 1318 | — |
Long Context Not comparable
Nemotron 3.5 Lightning: 39.9 (#165), Sonar: —
| Benchmark | Nemotron 3.5 Lightning | Sonar |
|---|---|---|
| LMArena Longer Query | 1314 | — |
Writing & Preference Sonar leads
Nemotron 3.5 Lightning: 48.5 (#201), Sonar: 52.6 (#167)
| Benchmark | Nemotron 3.5 Lightning | Sonar |
|---|---|---|
| LMArena Text | 1327 | — |
| LMArena Creative Writing | 1254 | — |
| EQ-Bench Creative Writing | 1280 | — |
| LMArena Multi-Turn | 1328 | — |
| LiveBench Language | — | 44.1% |
Frequently asked questions
Is Nemotron 3.5 Lightning better than Sonar?
Nemotron 3.5 Lightning is the stronger model overall, scoring 40.0 to 38.5 on the Noometry Index.
Which is cheaper, Nemotron 3.5 Lightning or Sonar?
Nemotron 3.5 Lightning 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 3.5 Lightning or Sonar better for coding?
Nemotron 3.5 Lightning scores higher on coding benchmarks: 40.4 versus 35.7 in the Noometry coding category.
Which has the bigger context window?
Nemotron 3.5 Lightning does, with 262K tokens against 128K.
How many benchmarks do Nemotron 3.5 Lightning and Sonar share?
0 benchmarks have published results for both models. Nemotron 3.5 Lightning has 18 scored results on Noometry and Sonar has 7.