Model comparison
Gemma 3 4B vs Nemotron 3.5 Lightning
Nemotron 3.5 Lightning is the stronger model overall, scoring 40.0 to 28.1 on the Noometry Index. Gemma 3 4B costs 1.8× less per token, which makes it the better buy when Nemotron 3.5 Lightning's lead doesn't matter for your workload.
Last verified . 13 shared benchmarks.
Google
NVIDIASummary
- They share 13 benchmarks with published results for both. Gemma 3 4B scores higher in 0 categories and Nemotron 3.5 Lightning in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Nemotron 3.5 Lightning leads 37.5 to 11.8.
- Gemma 3 4B is cheaper at $0.04 / $0.08 per million input/output tokens, against $0.05 / $0.20 for Nemotron 3.5 Lightning.
- Nemotron 3.5 Lightning accepts more context: 262K tokens versus 131K.
Side by side
| Gemma 3 4B | Nemotron 3.5 Lightning | |
|---|---|---|
| Provider | NVIDIA | |
| Noometry Index | 28.1 | 40.0 |
| Released | 2025-03-12 | 2026-08-11 |
| Weights | Open | Open |
| Context window | 131K | 262K |
| Max output | 4K | 262K |
| Input $ / M tokens | $0.04 | $0.05 |
| Output $ / M tokens | $0.08 | $0.20 |
| Results tracked | 22 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Nemotron 3.5 Lightning leads
Gemma 3 4B: 35.9 (#215), Nemotron 3.5 Lightning: 40.4 (#141)
| Benchmark | Gemma 3 4B | Nemotron 3.5 Lightning |
|---|---|---|
| LMArena Coding | 1230 | 1375 |
Agentic & Tool Use Not comparable
Gemma 3 4B: 20.9 (#142), Nemotron 3.5 Lightning: —
| Benchmark | Gemma 3 4B | Nemotron 3.5 Lightning |
|---|---|---|
| Berkeley Function Calling Leaderboard | 19.6% | — |
Reasoning Nemotron 3.5 Lightning leads
Gemma 3 4B: 13.2 (#335), Nemotron 3.5 Lightning: 26.8 (#127)
| Benchmark | Gemma 3 4B | Nemotron 3.5 Lightning |
|---|---|---|
| LMArena Hard Prompts | 1253 | 1337 |
| Kagi LLM Benchmark | 25.2% | — |
| Chess Puzzles | 0% | — |
| DTBench | 50.9% | — |
| LMCA | 2.8% | — |
| Epoch Capabilities Index | 116.02 | — |
Math Nemotron 3.5 Lightning leads
Gemma 3 4B: 16.8 (#292), Nemotron 3.5 Lightning: 37.5 (#155)
| Benchmark | Gemma 3 4B | Nemotron 3.5 Lightning |
|---|---|---|
| LMArena Math | 1239 | 1359 |
| OTIS Mock AIME 2024-2025 | 7.5% | — |
Knowledge Nemotron 3.5 Lightning leads
Gemma 3 4B: 11.8 (#299), Nemotron 3.5 Lightning: 37.5 (#154)
| Benchmark | Gemma 3 4B | Nemotron 3.5 Lightning |
|---|---|---|
| LMArena Expert | 1223 | 1356 |
| GPQA Diamond | 23.2% | — |
| Vectara Hallucination Rate | 6.4% | — |
Multilingual Nemotron 3.5 Lightning leads
Gemma 3 4B: 42.5 (#194), Nemotron 3.5 Lightning: 44.0 (#180)
| Benchmark | Gemma 3 4B | Nemotron 3.5 Lightning |
|---|---|---|
| LMArena Non-English | 1273 | 1295 |
| LMArena German | 1281 | 1282 |
| LMArena Russian | 1294 | 1253 |
| LMArena Chinese | — | 1359 |
| LMArena French | — | 1366 |
| LMArena Japanese | — | 1206 |
| LMArena Korean | — | 1238 |
| LMArena Spanish | — | 1345 |
Instruction Following Nemotron 3.5 Lightning leads
Gemma 3 4B: 65.2 (#225), Nemotron 3.5 Lightning: 69.6 (#170)
| Benchmark | Gemma 3 4B | Nemotron 3.5 Lightning |
|---|---|---|
| LMArena Instruction Following | 1239 | 1318 |
Long Context Nemotron 3.5 Lightning leads
Gemma 3 4B: 38.7 (#194), Nemotron 3.5 Lightning: 39.9 (#165)
| Benchmark | Gemma 3 4B | Nemotron 3.5 Lightning |
|---|---|---|
| LMArena Longer Query | 1273 | 1314 |
Writing & Preference Nemotron 3.5 Lightning leads
Gemma 3 4B: 42.0 (#239), Nemotron 3.5 Lightning: 48.5 (#201)
| Benchmark | Gemma 3 4B | Nemotron 3.5 Lightning |
|---|---|---|
| LMArena Text | 1291 | 1327 |
| LMArena Creative Writing | 1271 | 1254 |
| EQ-Bench Creative Writing | 1068 | 1280 |
| LMArena Multi-Turn | 1255 | 1328 |
Frequently asked questions
Is Gemma 3 4B better than Nemotron 3.5 Lightning?
Nemotron 3.5 Lightning is the stronger model overall, scoring 40.0 to 28.1 on the Noometry Index. Gemma 3 4B costs 1.8× less per token, which makes it the better buy when Nemotron 3.5 Lightning's lead doesn't matter for your workload.
Which is cheaper, Gemma 3 4B or Nemotron 3.5 Lightning?
Gemma 3 4B is cheaper. It lists at $0.04 per million input tokens and $0.08 per million output tokens; Nemotron 3.5 Lightning lists at $0.05 and $0.20.
Is Gemma 3 4B or Nemotron 3.5 Lightning better for coding?
Nemotron 3.5 Lightning scores higher on coding benchmarks: 40.4 versus 35.9 in the Noometry coding category.
Which has the bigger context window?
Nemotron 3.5 Lightning does, with 262K tokens against 131K.
How many benchmarks do Gemma 3 4B and Nemotron 3.5 Lightning share?
13 benchmarks have published results for both models. Gemma 3 4B has 22 scored results on Noometry and Nemotron 3.5 Lightning has 18.