Model comparison
Gemma 2 27B vs Nemotron 3 Ultra
Nemotron 3 Ultra is the stronger model overall, scoring 44.7 to 29.2 on the Noometry Index. Gemma 2 27B costs 1.6× less per token, which makes it the better buy when Nemotron 3 Ultra's lead doesn't matter for your workload.
Last verified . 21 shared benchmarks.
Google
NVIDIASummary
- They share 21 benchmarks with published results for both. Gemma 2 27B scores higher in 0 categories and Nemotron 3 Ultra in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Nemotron 3 Ultra leads 52.5 to 18.9.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 1.4% for Gemma 2 27B and 86.7% for Nemotron 3 Ultra.
- Gemma 2 27B is cheaper at $0.65 / $0.65 per million input/output tokens, against $0.60 / $2.40 for Nemotron 3 Ultra.
- Nemotron 3 Ultra accepts more context: 262K tokens versus 8K.
Side by side
| Gemma 2 27B | Nemotron 3 Ultra | |
|---|---|---|
| Provider | NVIDIA | |
| Noometry Index | 29.2 | 44.7 |
| Released | 2024-06-24 | 2026-06-04 |
| Weights | Open | Open |
| Context window | 8K | 262K |
| Max output | 2K | 128K |
| Input $ / M tokens | $0.65 | $0.60 |
| Output $ / M tokens | $0.65 | $2.40 |
| Results tracked | 34 | 29 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Nemotron 3 Ultra leads
Gemma 2 27B: 33.5 (#243), Nemotron 3 Ultra: 37.7 (#174)
| Benchmark | Gemma 2 27B | Nemotron 3 Ultra |
|---|---|---|
| LMArena Coding | 1211 | 1468 |
| FrontierCode | — | 13.6% |
| SciCode | — | 40.3% |
| WeirdML | — | 43.5% |
| BigCodeBench Instruct | 42.8% | — |
| LiveBench Coding | 36% | — |
| BigCodeBench Complete | 52.5% | — |
Reasoning Nemotron 3 Ultra leads
Gemma 2 27B: 14.8 (#313), Nemotron 3 Ultra: 30.3 (#78)
| Benchmark | Gemma 2 27B | Nemotron 3 Ultra |
|---|---|---|
| LMArena Hard Prompts | 1199 | 1452 |
| DTBench | 48% | 90.1% |
| LMCA | 7.1% | 36.9% |
| Epoch Capabilities Index | 122.06 | 146.2 |
| CritPt | — | 3.1% |
| Chess Puzzles | — | 12% |
| LiveBench Reasoning | 28.1% | — |
| Mystery Game Puzzles | — | 20% |
| LiveBench Data Analysis | 47.9% | — |
| LiveBench | 38.2% | — |
Math Nemotron 3 Ultra leads
Gemma 2 27B: 10.0 (#306), Nemotron 3 Ultra: 34.4 (#160)
| Benchmark | Gemma 2 27B | Nemotron 3 Ultra |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.4% | 86.7% |
| LMArena Math | 1212 | 1456 |
| ProofBench | — | 2% |
| LiveBench Math | 26.5% | — |
| MATH Level 5 | 27.9% | — |
Knowledge Nemotron 3 Ultra leads
Gemma 2 27B: 18.9 (#275), Nemotron 3 Ultra: 52.5 (#56)
| Benchmark | Gemma 2 27B | Nemotron 3 Ultra |
|---|---|---|
| GPQA Diamond | 36.5% | 85.4% |
| LMArena Expert | 1172 | 1472 |
| Confabulations | 27.1% | — |
| MMLU | 75.7% | — |
Multilingual Nemotron 3 Ultra leads
Gemma 2 27B: 38.8 (#221), Nemotron 3 Ultra: 53.7 (#61)
| Benchmark | Gemma 2 27B | Nemotron 3 Ultra |
|---|---|---|
| LMArena Non-English | 1217 | 1427 |
| LMArena Chinese | 1221 | 1498 |
| LMArena French | 1246 | 1475 |
| LMArena German | 1209 | 1471 |
| LMArena Korean | 1174 | 1387 |
| LMArena Russian | 1234 | 1415 |
| LMArena Spanish | 1228 | 1452 |
| LMArena Japanese | 1175 | — |
Instruction Following Nemotron 3 Ultra leads
Gemma 2 27B: 60.7 (#244), Nemotron 3 Ultra: 74.9 (#84)
| Benchmark | Gemma 2 27B | Nemotron 3 Ultra |
|---|---|---|
| LMArena Instruction Following | 1206 | 1417 |
| LiveBench Instruction Following | 58.1% | — |
Long Context Nemotron 3 Ultra leads
Gemma 2 27B: 37.3 (#213), Nemotron 3 Ultra: 43.9 (#77)
| Benchmark | Gemma 2 27B | Nemotron 3 Ultra |
|---|---|---|
| LMArena Longer Query | 1231 | 1437 |
Writing & Preference Nemotron 3 Ultra leads
Gemma 2 27B: 44.4 (#220), Nemotron 3 Ultra: 66.3 (#35)
| Benchmark | Gemma 2 27B | Nemotron 3 Ultra |
|---|---|---|
| LMArena Text | 1231 | 1444 |
| LMArena Creative Writing | 1241 | 1392 |
| LMArena Multi-Turn | 1224 | 1412 |
| EQ-Bench Creative Writing | — | 1692 |
| LiveBench Language | 32.6% | — |
Frequently asked questions
Is Gemma 2 27B better than Nemotron 3 Ultra?
Nemotron 3 Ultra is the stronger model overall, scoring 44.7 to 29.2 on the Noometry Index. Gemma 2 27B costs 1.6× 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 2 27B or Nemotron 3 Ultra?
Gemma 2 27B is cheaper. It lists at $0.65 per million input tokens and $0.65 per million output tokens; Nemotron 3 Ultra lists at $0.60 and $2.40.
Is Gemma 2 27B or Nemotron 3 Ultra better for coding?
Nemotron 3 Ultra scores higher on coding benchmarks: 37.7 versus 33.5 in the Noometry coding category.
Which has the bigger context window?
Nemotron 3 Ultra does, with 262K tokens against 8K.
How many benchmarks do Gemma 2 27B and Nemotron 3 Ultra share?
21 benchmarks have published results for both models. Gemma 2 27B has 34 scored results on Noometry and Nemotron 3 Ultra has 29.