Model comparison
Gemma 3 27B vs Nemotron 3 Super
Nemotron 3 Super is the stronger model overall, scoring 40.1 to 30.8 on the Noometry Index. Gemma 3 27B costs 1.7× less per token, which makes it the better buy when Nemotron 3 Super's lead doesn't matter for your workload.
Last verified . 17 shared benchmarks.
Google
NVIDIASummary
- They share 17 benchmarks with published results for both. Gemma 3 27B scores higher in 0 categories and Nemotron 3 Super in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in coding, where Nemotron 3 Super leads 39.4 to 22.5.
- The biggest single-benchmark swing is SciCode: 21.2% for Gemma 3 27B and 36% for Nemotron 3 Super.
- Gemma 3 27B is cheaper at $0.08 / $0.16 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 27B | Nemotron 3 Super | |
|---|---|---|
| Provider | NVIDIA | |
| Noometry Index | 30.8 | 40.1 |
| Released | 2025-03-11 | 2026-03-11 |
| Weights | Open | Open |
| Context window | 131K | 262K |
| Max output | 8K | 131K |
| Input $ / M tokens | $0.08 | $0.08 |
| Output $ / M tokens | $0.16 | $0.45 |
| Results tracked | 43 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Nemotron 3 Super leads
Gemma 3 27B: 22.5 (#334), Nemotron 3 Super: 39.4 (#158)
| Benchmark | Gemma 3 27B | Nemotron 3 Super |
|---|---|---|
| SciCode | 21.2% | 36% |
| LMArena Coding | 1322 | 1403 |
| Aider Polyglot | 4.9% | — |
| WeirdML | — | 38% |
| LiveBench Coding | 39.9% | — |
| ALE-Bench | — | 213.9 |
Agentic & Tool Use Not comparable
Gemma 3 27B: 25.1 (#110), Nemotron 3 Super: —
| Benchmark | Gemma 3 27B | Nemotron 3 Super |
|---|---|---|
| Berkeley Function Calling Leaderboard | 29.5% | — |
Reasoning Nemotron 3 Super leads
Gemma 3 27B: 16.7 (#301), Nemotron 3 Super: 18.7 (#276)
| Benchmark | Gemma 3 27B | Nemotron 3 Super |
|---|---|---|
| CritPt | 0% | 3.1% |
| LMArena Hard Prompts | 1340 | 1386 |
| Kagi LLM Benchmark | 40.4% | — |
| NYT Connections (extended) | — | 15.4% |
| Chess Puzzles | 0% | — |
| LiveBench Reasoning | 43.8% | — |
| DTBench | 52.5% | — |
| LiveBench Data Analysis | 51.5% | — |
| LMCA | 12.3% | — |
| Epoch Capabilities Index | 130.04 | — |
| LiveBench | 50% | — |
Math Nemotron 3 Super leads
Gemma 3 27B: 25.9 (#265), Nemotron 3 Super: 39.6 (#101)
| Benchmark | Gemma 3 27B | Nemotron 3 Super |
|---|---|---|
| LMArena Math | 1312 | 1380 |
| MathArena Final-Answer Competitions | — | 60.4% |
| OTIS Mock AIME 2024-2025 | 22.5% | — |
| LiveBench Math | 55.4% | — |
| MATH Level 5 | 74% | — |
Knowledge Nemotron 3 Super leads
Gemma 3 27B: 25.5 (#261), Nemotron 3 Super: 38.9 (#139)
| Benchmark | Gemma 3 27B | Nemotron 3 Super |
|---|---|---|
| LMArena Expert | 1304 | 1398 |
| GPQA Diamond | 47.7% | — |
| Confabulations | 40.3% | — |
| Vectara Hallucination Rate | 7.4% | — |
Multimodal Not comparable
Gemma 3 27B: 32.6 (#100), Nemotron 3 Super: —
| Benchmark | Gemma 3 27B | Nemotron 3 Super |
|---|---|---|
| LMArena Vision | 1164 | — |
| GeoBench | 52% | — |
Multilingual Nemotron 3 Super leads
Gemma 3 27B: 46.9 (#155), Nemotron 3 Super: 48.4 (#144)
| Benchmark | Gemma 3 27B | Nemotron 3 Super |
|---|---|---|
| LMArena Non-English | 1334 | 1355 |
| LMArena Chinese | 1346 | 1432 |
| LMArena French | 1368 | 1405 |
| LMArena German | 1362 | 1341 |
| LMArena Russian | 1349 | 1336 |
| LMArena Spanish | 1349 | 1417 |
| LMArena Japanese | 1287 | — |
| LMArena Korean | 1308 | — |
Instruction Following Too close to call
Gemma 3 27B: 70.6 (#160), Nemotron 3 Super: 71.2 (#154)
| Benchmark | Gemma 3 27B | Nemotron 3 Super |
|---|---|---|
| LMArena Instruction Following | 1321 | 1347 |
| LiveBench Instruction Following | 74.9% | — |
Long Context Nemotron 3 Super leads
Gemma 3 27B: 27.6 (#293), Nemotron 3 Super: 41.5 (#139)
| Benchmark | Gemma 3 27B | Nemotron 3 Super |
|---|---|---|
| LMArena Longer Query | 1333 | 1362 |
| Fiction.LiveBench | 33.3% | — |
Writing & Preference Nemotron 3 Super leads
Gemma 3 27B: 52.5 (#168), Nemotron 3 Super: 55.9 (#140)
| Benchmark | Gemma 3 27B | Nemotron 3 Super |
|---|---|---|
| LMArena Text | 1358 | 1378 |
| LMArena Creative Writing | 1346 | 1317 |
| LMArena Multi-Turn | 1345 | 1369 |
| Short-Story Creative Writing | 79.9% | — |
| EQ-Bench Creative Writing | 1266 | — |
| LiveBench Language | 34.6% | — |
Frequently asked questions
Is Gemma 3 27B better than Nemotron 3 Super?
Nemotron 3 Super is the stronger model overall, scoring 40.1 to 30.8 on the Noometry Index. Gemma 3 27B costs 1.7× 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 27B or Nemotron 3 Super?
Gemma 3 27B is cheaper. It lists at $0.08 per million input tokens and $0.16 per million output tokens; Nemotron 3 Super lists at $0.08 and $0.45.
Is Gemma 3 27B or Nemotron 3 Super better for coding?
Nemotron 3 Super scores higher on coding benchmarks: 39.4 versus 22.5 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 27B and Nemotron 3 Super share?
17 benchmarks have published results for both models. Gemma 3 27B has 43 scored results on Noometry and Nemotron 3 Super has 21.