Model comparison
Gemma 3 4B vs Nemotron 3 Super
Nemotron 3 Super is the stronger model overall, scoring 39.6 to 27.9 on the Noometry Index. Gemma 3 4B costs 3.4× less per token, which makes it the better buy when Nemotron 3 Super's lead doesn't matter for your workload.
Last verified . 12 shared benchmarks.
Google
NVIDIASummary
- They share 12 benchmarks with published results for both. Gemma 3 4B scores higher in 0 categories and Nemotron 3 Super in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Nemotron 3 Super leads 38.2 to 11.8.
- Gemma 3 4B is cheaper at $0.04 / $0.08 per million input/output tokens, against $0.08 / $0.45 for Nemotron 3 Super.
- Nemotron 3 Super accepts more context: 262K tokens versus 131K.
Side by side
| Gemma 3 4B | Nemotron 3 Super | |
|---|---|---|
| Provider | NVIDIA | |
| Noometry Index | 27.9 | 39.6 |
| Released | 2025-03-12 | 2026-03-11 |
| Weights | Open | Open |
| Context window | 131K | 262K |
| Max output | 4K | 131K |
| Input $ / M tokens | $0.04 | $0.08 |
| Output $ / M tokens | $0.08 | $0.45 |
| Results tracked | 22 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Nemotron 3 Super leads
Gemma 3 4B: 35.3 (#214), Nemotron 3 Super: 38.9 (#153)
| Benchmark | Gemma 3 4B | Nemotron 3 Super |
|---|---|---|
| LMArena Coding | 1230 | 1403 |
| SciCode | — | 36% |
| WeirdML | — | 38% |
| ALE-Bench | — | 213.9 |
Agentic & Tool Use Not comparable
Gemma 3 4B: 20.7 (#134), Nemotron 3 Super: —
| Benchmark | Gemma 3 4B | Nemotron 3 Super |
|---|---|---|
| Berkeley Function Calling Leaderboard | 19.6% | — |
Reasoning Nemotron 3 Super leads
Gemma 3 4B: 12.7 (#330), Nemotron 3 Super: 17.9 (#274)
| Benchmark | Gemma 3 4B | Nemotron 3 Super |
|---|---|---|
| LMArena Hard Prompts | 1253 | 1386 |
| Kagi LLM Benchmark | 25.2% | — |
| NYT Connections (extended) | — | 15.4% |
| CritPt | — | 3.1% |
| Chess Puzzles | 0% | — |
| DTBench | 50.9% | — |
| LMCA | 2.8% | — |
| Epoch Capabilities Index | 116.02 | — |
Math Nemotron 3 Super leads
Gemma 3 4B: 15.8 (#286), Nemotron 3 Super: 37.6 (#95)
| Benchmark | Gemma 3 4B | Nemotron 3 Super |
|---|---|---|
| LMArena Math | 1239 | 1381 |
| MathArena Final-Answer Competitions | — | 60.4% |
| OTIS Mock AIME 2024-2025 | 7.5% | — |
Knowledge Nemotron 3 Super leads
Gemma 3 4B: 11.8 (#294), Nemotron 3 Super: 38.2 (#136)
| Benchmark | Gemma 3 4B | Nemotron 3 Super |
|---|---|---|
| LMArena Expert | 1223 | 1397 |
| GPQA Diamond | 23.2% | — |
| Vectara Hallucination Rate | 6.4% | — |
Multilingual Nemotron 3 Super leads
Gemma 3 4B: 42.7 (#189), Nemotron 3 Super: 48.6 (#139)
| Benchmark | Gemma 3 4B | Nemotron 3 Super |
|---|---|---|
| LMArena Non-English | 1273 | 1356 |
| LMArena German | 1281 | 1341 |
| LMArena Russian | 1294 | 1336 |
| LMArena Chinese | — | 1430 |
| LMArena French | — | 1404 |
| LMArena Spanish | — | 1417 |
Instruction Following Nemotron 3 Super leads
Gemma 3 4B: 65.4 (#219), Nemotron 3 Super: 71.4 (#149)
| Benchmark | Gemma 3 4B | Nemotron 3 Super |
|---|---|---|
| LMArena Instruction Following | 1239 | 1347 |
Long Context Nemotron 3 Super leads
Gemma 3 4B: 38.6 (#189), Nemotron 3 Super: 41.5 (#134)
| Benchmark | Gemma 3 4B | Nemotron 3 Super |
|---|---|---|
| LMArena Longer Query | 1274 | 1362 |
Writing & Preference Nemotron 3 Super leads
Gemma 3 4B: 42.2 (#234), Nemotron 3 Super: 56.1 (#135)
| Benchmark | Gemma 3 4B | Nemotron 3 Super |
|---|---|---|
| LMArena Text | 1291 | 1378 |
| LMArena Creative Writing | 1270 | 1317 |
| LMArena Multi-Turn | 1255 | 1369 |
| EQ-Bench Creative Writing | 1068 | — |
Frequently asked questions
Is Gemma 3 4B better than Nemotron 3 Super?
Nemotron 3 Super is the stronger model overall, scoring 39.6 to 27.9 on the Noometry Index. Gemma 3 4B costs 3.4× less per token, which makes it the better buy when Nemotron 3 Super's lead doesn't matter for your workload.
Which is cheaper, Gemma 3 4B or Nemotron 3 Super?
Gemma 3 4B is cheaper. It lists at $0.04 per million input tokens and $0.08 per million output tokens; Nemotron 3 Super lists at $0.08 and $0.45.
Is Gemma 3 4B or Nemotron 3 Super better for coding?
Nemotron 3 Super scores higher on coding benchmarks: 38.9 versus 35.3 in the Noometry coding category.
Which has the bigger context window?
Nemotron 3 Super does, with 262K tokens against 131K.
How many benchmarks do Gemma 3 4B and Nemotron 3 Super share?
12 benchmarks have published results for both models. Gemma 3 4B has 22 scored results on Noometry and Nemotron 3 Super has 21.