Model comparison
Gemma 3 27B vs Nemotron 3 Ultra
Nemotron 3 Ultra is the stronger model overall, scoring 42.5 to 30.8 on the Noometry Index. Gemma 3 27B costs 10× less per token, which makes it the better buy when Nemotron 3 Ultra's lead doesn't matter for your workload.
Last verified . 25 shared benchmarks.
Google
NVIDIASummary
- They share 25 benchmarks with published results for both. Gemma 3 27B scores higher in 1 category and Nemotron 3 Ultra in 8 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Nemotron 3 Ultra leads 52.5 to 25.5.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 22.5% for Gemma 3 27B and 86.7% for Nemotron 3 Ultra.
- Gemma 3 27B is cheaper at $0.08 / $0.16 per million input/output tokens, against $0.60 / $2.40 for Nemotron 3 Ultra.
- Nemotron 3 Ultra accepts more context: 262K tokens versus 131K.
Side by side
| Gemma 3 27B | Nemotron 3 Ultra | |
|---|---|---|
| Provider | NVIDIA | |
| Noometry Index | 30.8 | 42.5 |
| Released | 2025-03-11 | 2026-06-04 |
| Weights | Open | Open |
| Context window | 131K | 262K |
| Max output | 8K | 128K |
| Input $ / M tokens | $0.08 | $0.60 |
| Output $ / M tokens | $0.16 | $2.40 |
| Results tracked | 43 | 30 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Nemotron 3 Ultra leads
Gemma 3 27B: 22.5 (#334), Nemotron 3 Ultra: 38.1 (#182)
| Benchmark | Gemma 3 27B | Nemotron 3 Ultra |
|---|---|---|
| SciCode | 21.2% | 40.3% |
| LMArena Coding | 1322 | 1468 |
| FrontierCode | — | 13.6% |
| Aider Polyglot | 4.9% | — |
| WeirdML | — | 43.5% |
| LiveBench Coding | 39.9% | — |
Agentic & Tool Use Gemma 3 27B leads
Gemma 3 27B: 25.1 (#110), Nemotron 3 Ultra: 23.4 (#126)
| Benchmark | Gemma 3 27B | Nemotron 3 Ultra |
|---|---|---|
| APEX-Agents | — | 22.7% |
| Berkeley Function Calling Leaderboard | 29.5% | — |
Reasoning Nemotron 3 Ultra leads
Gemma 3 27B: 16.7 (#301), Nemotron 3 Ultra: 31.0 (#82)
| Benchmark | Gemma 3 27B | Nemotron 3 Ultra |
|---|---|---|
| CritPt | 0% | 3.1% |
| Chess Puzzles | 0% | 12% |
| LMArena Hard Prompts | 1340 | 1452 |
| DTBench | 52.5% | 90.1% |
| LMCA | 12.3% | 36.9% |
| Epoch Capabilities Index | 130.04 | 146.17 |
| Kagi LLM Benchmark | 40.4% | — |
| LiveBench Reasoning | 43.8% | — |
| Mystery Game Puzzles | — | 20% |
| LiveBench Data Analysis | 51.5% | — |
| LiveBench | 50% | — |
Math Nemotron 3 Ultra leads
Gemma 3 27B: 25.9 (#265), Nemotron 3 Ultra: 35.3 (#187)
| Benchmark | Gemma 3 27B | Nemotron 3 Ultra |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 22.5% | 86.7% |
| LMArena Math | 1312 | 1457 |
| ProofBench | — | 2% |
| LiveBench Math | 55.4% | — |
| MATH Level 5 | 74% | — |
Knowledge Nemotron 3 Ultra leads
Gemma 3 27B: 25.5 (#261), Nemotron 3 Ultra: 52.5 (#61)
| Benchmark | Gemma 3 27B | Nemotron 3 Ultra |
|---|---|---|
| GPQA Diamond | 47.7% | 85.4% |
| LMArena Expert | 1304 | 1472 |
| Confabulations | 40.3% | — |
| Vectara Hallucination Rate | 7.4% | — |
Multimodal Not comparable
Gemma 3 27B: 32.6 (#100), Nemotron 3 Ultra: —
| Benchmark | Gemma 3 27B | Nemotron 3 Ultra |
|---|---|---|
| LMArena Vision | 1164 | — |
| GeoBench | 52% | — |
Multilingual Nemotron 3 Ultra leads
Gemma 3 27B: 46.9 (#155), Nemotron 3 Ultra: 53.5 (#64)
| Benchmark | Gemma 3 27B | Nemotron 3 Ultra |
|---|---|---|
| LMArena Non-English | 1334 | 1427 |
| LMArena Chinese | 1346 | 1497 |
| LMArena French | 1368 | 1472 |
| LMArena German | 1362 | 1471 |
| LMArena Korean | 1308 | 1386 |
| LMArena Russian | 1349 | 1417 |
| LMArena Spanish | 1349 | 1454 |
| LMArena Japanese | 1287 | — |
Instruction Following Nemotron 3 Ultra leads
Gemma 3 27B: 70.6 (#160), Nemotron 3 Ultra: 74.7 (#88)
| Benchmark | Gemma 3 27B | Nemotron 3 Ultra |
|---|---|---|
| LMArena Instruction Following | 1321 | 1418 |
| LiveBench Instruction Following | 74.9% | — |
Long Context Nemotron 3 Ultra leads
Gemma 3 27B: 27.6 (#293), Nemotron 3 Ultra: 43.9 (#81)
| Benchmark | Gemma 3 27B | Nemotron 3 Ultra |
|---|---|---|
| LMArena Longer Query | 1333 | 1437 |
| Fiction.LiveBench | 33.3% | — |
Writing & Preference Nemotron 3 Ultra leads
Gemma 3 27B: 52.5 (#168), Nemotron 3 Ultra: 66.3 (#36)
| Benchmark | Gemma 3 27B | Nemotron 3 Ultra |
|---|---|---|
| LMArena Text | 1358 | 1445 |
| LMArena Creative Writing | 1346 | 1398 |
| EQ-Bench Creative Writing | 1266 | 1692 |
| LMArena Multi-Turn | 1345 | 1411 |
| Short-Story Creative Writing | 79.9% | — |
| LiveBench Language | 34.6% | — |
Frequently asked questions
Is Gemma 3 27B better than Nemotron 3 Ultra?
Nemotron 3 Ultra is the stronger model overall, scoring 42.5 to 30.8 on the Noometry Index. Gemma 3 27B costs 10× less per token, which makes it the better buy when Nemotron 3 Ultra's lead doesn't matter for your workload.
Which is cheaper, Gemma 3 27B or Nemotron 3 Ultra?
Gemma 3 27B is cheaper. It lists at $0.08 per million input tokens and $0.16 per million output tokens; Nemotron 3 Ultra lists at $0.60 and $2.40.
Is Gemma 3 27B or Nemotron 3 Ultra better for coding?
Nemotron 3 Ultra scores higher on coding benchmarks: 38.1 versus 22.5 in the Noometry coding category.
Which has the bigger context window?
Nemotron 3 Ultra does, with 262K tokens against 131K.
How many benchmarks do Gemma 3 27B and Nemotron 3 Ultra share?
25 benchmarks have published results for both models. Gemma 3 27B has 43 scored results on Noometry and Nemotron 3 Ultra has 30.