Model comparison
Gemma 4 31B IT vs Nemotron 3 Super
Gemma 4 31B IT is the stronger model overall, scoring 43.5 to 40.1 on the Noometry Index.
Last verified . 19 shared benchmarks.
Google
NVIDIASummary
- They share 19 benchmarks with published results for both. Gemma 4 31B IT scores higher in 7 categories and Nemotron 3 Super in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemma 4 31B IT leads 27.2 to 18.7.
- The biggest single-benchmark swing is NYT Connections (extended): 70.6% for Gemma 4 31B IT and 15.4% for Nemotron 3 Super.
- Gemma 4 31B IT is cheaper at $0.09 / $0.34 per million input/output tokens, against $0.08 / $0.45 for Nemotron 3 Super.
Side by side
| Gemma 4 31B IT | Nemotron 3 Super | |
|---|---|---|
| Provider | NVIDIA | |
| Noometry Index | 43.5 | 40.1 |
| Released | 2026-04-02 | 2026-03-11 |
| Weights | Open | Open |
| Context window | 262K | 262K |
| Max output | 33K | 131K |
| Input $ / M tokens | $0.09 | $0.08 |
| Output $ / M tokens | $0.34 | $0.45 |
| Results tracked | 35 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 4 31B IT leads
Gemma 4 31B IT: 42.3 (#108), Nemotron 3 Super: 39.4 (#158)
| Benchmark | Gemma 4 31B IT | Nemotron 3 Super |
|---|---|---|
| SciCode | 43.4% | 36% |
| WeirdML | 52.3% | 38% |
| LMArena Coding | 1459 | 1403 |
| ALE-Bench | 925.5 | 213.9 |
| LMArena WebDev | 1366 | — |
Reasoning Gemma 4 31B IT leads
Gemma 4 31B IT: 27.2 (#122), Nemotron 3 Super: 18.7 (#276)
| Benchmark | Gemma 4 31B IT | Nemotron 3 Super |
|---|---|---|
| NYT Connections (extended) | 70.6% | 15.4% |
| CritPt | 1.4% | 3.1% |
| LMArena Hard Prompts | 1448 | 1386 |
| Kagi LLM Benchmark | 63.5% | — |
| Chess Puzzles | 5% | — |
| Thematic Generalization | 53% | — |
| DTBench | 82.7% | — |
| LMCA | 39.3% | — |
| Surface Evolver Bench | 30.6% | — |
| Epoch Capabilities Index | 142.74 | — |
Math Gemma 4 31B IT leads
Gemma 4 31B IT: 43.2 (#81), Nemotron 3 Super: 39.6 (#101)
| Benchmark | Gemma 4 31B IT | Nemotron 3 Super |
|---|---|---|
| LMArena Math | 1465 | 1380 |
| MathArena Final-Answer Competitions | — | 60.4% |
| OTIS Mock AIME 2024-2025 | 73.3% | — |
Knowledge Too close to call
Gemma 4 31B IT: 37.9 (#151), Nemotron 3 Super: 38.9 (#139)
| Benchmark | Gemma 4 31B IT | Nemotron 3 Super |
|---|---|---|
| LMArena Expert | 1465 | 1398 |
| GPQA Diamond | 75.8% | — |
| SimpleQA Verified | 10.4% | — |
| Vectara Hallucination Rate | 7.4% | — |
Multimodal Not comparable
Gemma 4 31B IT: 41.6 (#34), Nemotron 3 Super: —
| Benchmark | Gemma 4 31B IT | Nemotron 3 Super |
|---|---|---|
| LMArena Vision | 1277 | — |
| LMArena Document | 1425 | — |
Multilingual Gemma 4 31B IT leads
Gemma 4 31B IT: 53.8 (#57), Nemotron 3 Super: 48.4 (#144)
| Benchmark | Gemma 4 31B IT | Nemotron 3 Super |
|---|---|---|
| LMArena Non-English | 1431 | 1355 |
| LMArena Chinese | 1476 | 1432 |
| LMArena French | 1435 | 1405 |
| LMArena Russian | 1460 | 1336 |
| LMArena Spanish | 1444 | 1417 |
| LMArena German | — | 1341 |
Instruction Following Gemma 4 31B IT leads
Gemma 4 31B IT: 75.5 (#61), Nemotron 3 Super: 71.2 (#154)
| Benchmark | Gemma 4 31B IT | Nemotron 3 Super |
|---|---|---|
| LMArena Instruction Following | 1433 | 1347 |
Long Context Gemma 4 31B IT leads
Gemma 4 31B IT: 44.2 (#71), Nemotron 3 Super: 41.5 (#139)
| Benchmark | Gemma 4 31B IT | Nemotron 3 Super |
|---|---|---|
| LMArena Longer Query | 1446 | 1362 |
Writing & Preference Gemma 4 31B IT leads
Gemma 4 31B IT: 60.5 (#96), Nemotron 3 Super: 55.9 (#140)
| Benchmark | Gemma 4 31B IT | Nemotron 3 Super |
|---|---|---|
| LMArena Text | 1443 | 1378 |
| LMArena Creative Writing | 1415 | 1317 |
| LMArena Multi-Turn | 1452 | 1369 |
| EQ-Bench Creative Writing | 1368 | — |
| EQ-Bench 4 | 1120 | — |
Frequently asked questions
Is Gemma 4 31B IT better than Nemotron 3 Super?
Gemma 4 31B IT is the stronger model overall, scoring 43.5 to 40.1 on the Noometry Index.
Which is cheaper, Gemma 4 31B IT or Nemotron 3 Super?
Gemma 4 31B IT is cheaper. It lists at $0.09 per million input tokens and $0.34 per million output tokens; Nemotron 3 Super lists at $0.08 and $0.45.
Is Gemma 4 31B IT or Nemotron 3 Super better for coding?
Gemma 4 31B IT scores higher on coding benchmarks: 42.3 versus 39.4 in the Noometry coding category.
Which has the bigger context window?
Both accept 262K tokens.
How many benchmarks do Gemma 4 31B IT and Nemotron 3 Super share?
19 benchmarks have published results for both models. Gemma 4 31B IT has 35 scored results on Noometry and Nemotron 3 Super has 21.