Model comparison
Gemma 2 27B vs Nvidia Llama 3.3 Nemotron Super 49b v1.5
Nvidia Llama 3.3 Nemotron Super 49b v1.5 is the stronger model overall, scoring 40.3 to 29.4 on the Noometry Index.
Last verified . 12 shared benchmarks.
Google
NVIDIASummary
- They share 12 benchmarks with published results for both. Gemma 2 27B scores higher in 0 categories and Nvidia Llama 3.3 Nemotron Super 49b v1.5 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Nvidia Llama 3.3 Nemotron Super 49b v1.5 leads 38.2 to 10.7.
- Nvidia Llama 3.3 Nemotron Super 49b v1.5 is cheaper at $0.40 / $0.40 per million input/output tokens, against $0.65 / $0.65 for Gemma 2 27B.
- Nvidia Llama 3.3 Nemotron Super 49b v1.5 accepts more context: 131K tokens versus 8K.
Side by side
| Gemma 2 27B | Nvidia Llama 3.3 Nemotron Super 49b v1.5 | |
|---|---|---|
| Provider | NVIDIA | |
| Noometry Index | 29.4 | 40.3 |
| Released | 2024-06-24 | 2025-07-25 |
| Weights | Open | Open |
| Context window | 8K | 131K |
| Max output | 2K | 131K |
| Input $ / M tokens | $0.65 | $0.40 |
| Output $ / M tokens | $0.65 | $0.40 |
| Results tracked | 34 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Nvidia Llama 3.3 Nemotron Super 49b v1.5 leads
Gemma 2 27B: 34.1 (#246), Nvidia Llama 3.3 Nemotron Super 49b v1.5: 39.8 (#154)
| Benchmark | Gemma 2 27B | Nvidia Llama 3.3 Nemotron Super 49b v1.5 |
|---|---|---|
| LMArena Coding | 1211 | 1355 |
| BigCodeBench Instruct | 42.8% | — |
| LiveBench Coding | 36% | — |
| BigCodeBench Complete | 52.5% | — |
Reasoning Nvidia Llama 3.3 Nemotron Super 49b v1.5 leads
Gemma 2 27B: 15.3 (#315), Nvidia Llama 3.3 Nemotron Super 49b v1.5: 26.8 (#128)
| Benchmark | Gemma 2 27B | Nvidia Llama 3.3 Nemotron Super 49b v1.5 |
|---|---|---|
| LMArena Hard Prompts | 1198 | 1336 |
| LiveBench Reasoning | 28.1% | — |
| DTBench | 48% | — |
| LiveBench Data Analysis | 47.9% | — |
| LMCA | 7.1% | — |
| Epoch Capabilities Index | 122.08 | — |
| LiveBench | 38.2% | — |
Math Nvidia Llama 3.3 Nemotron Super 49b v1.5 leads
Gemma 2 27B: 10.7 (#311), Nvidia Llama 3.3 Nemotron Super 49b v1.5: 38.2 (#141)
| Benchmark | Gemma 2 27B | Nvidia Llama 3.3 Nemotron Super 49b v1.5 |
|---|---|---|
| LMArena Math | 1212 | 1392 |
| OTIS Mock AIME 2024-2025 | 1.4% | — |
| LiveBench Math | 26.5% | — |
| MATH Level 5 | 27.9% | — |
Knowledge Nvidia Llama 3.3 Nemotron Super 49b v1.5 leads
Gemma 2 27B: 19.0 (#280), Nvidia Llama 3.3 Nemotron Super 49b v1.5: 36.7 (#165)
| Benchmark | Gemma 2 27B | Nvidia Llama 3.3 Nemotron Super 49b v1.5 |
|---|---|---|
| LMArena Expert | 1172 | 1330 |
| GPQA Diamond | 36.5% | — |
| Confabulations | 27.1% | — |
| MMLU | 75.7% | — |
Multilingual Nvidia Llama 3.3 Nemotron Super 49b v1.5 leads
Gemma 2 27B: 38.6 (#226), Nvidia Llama 3.3 Nemotron Super 49b v1.5: 45.5 (#168)
| Benchmark | Gemma 2 27B | Nvidia Llama 3.3 Nemotron Super 49b v1.5 |
|---|---|---|
| LMArena Non-English | 1217 | 1316 |
| LMArena Japanese | 1175 | 1300 |
| LMArena Russian | 1234 | 1332 |
| LMArena Chinese | 1221 | — |
| LMArena French | 1247 | — |
| LMArena German | 1209 | — |
| LMArena Korean | 1174 | — |
| LMArena Spanish | 1228 | — |
Instruction Following Nvidia Llama 3.3 Nemotron Super 49b v1.5 leads
Gemma 2 27B: 60.5 (#249), Nvidia Llama 3.3 Nemotron Super 49b v1.5: 68.6 (#188)
| Benchmark | Gemma 2 27B | Nvidia Llama 3.3 Nemotron Super 49b v1.5 |
|---|---|---|
| LMArena Instruction Following | 1206 | 1299 |
| LiveBench Instruction Following | 58.1% | — |
Long Context Nvidia Llama 3.3 Nemotron Super 49b v1.5 leads
Gemma 2 27B: 37.3 (#218), Nvidia Llama 3.3 Nemotron Super 49b v1.5: 40.0 (#164)
| Benchmark | Gemma 2 27B | Nvidia Llama 3.3 Nemotron Super 49b v1.5 |
|---|---|---|
| LMArena Longer Query | 1231 | 1315 |
Writing & Preference Nvidia Llama 3.3 Nemotron Super 49b v1.5 leads
Gemma 2 27B: 44.2 (#225), Nvidia Llama 3.3 Nemotron Super 49b v1.5: 53.1 (#159)
| Benchmark | Gemma 2 27B | Nvidia Llama 3.3 Nemotron Super 49b v1.5 |
|---|---|---|
| LMArena Text | 1231 | 1338 |
| LMArena Creative Writing | 1241 | 1307 |
| LMArena Multi-Turn | 1224 | 1334 |
| LiveBench Language | 32.6% | — |
Frequently asked questions
Is Gemma 2 27B better than Nvidia Llama 3.3 Nemotron Super 49b v1.5?
Nvidia Llama 3.3 Nemotron Super 49b v1.5 is the stronger model overall, scoring 40.3 to 29.4 on the Noometry Index.
Which is cheaper, Gemma 2 27B or Nvidia Llama 3.3 Nemotron Super 49b v1.5?
Nvidia Llama 3.3 Nemotron Super 49b v1.5 is cheaper. It lists at $0.40 per million input tokens and $0.40 per million output tokens; Gemma 2 27B lists at $0.65 and $0.65.
Is Gemma 2 27B or Nvidia Llama 3.3 Nemotron Super 49b v1.5 better for coding?
Nvidia Llama 3.3 Nemotron Super 49b v1.5 scores higher on coding benchmarks: 39.8 versus 34.1 in the Noometry coding category.
Which has the bigger context window?
Nvidia Llama 3.3 Nemotron Super 49b v1.5 does, with 131K tokens against 8K.
How many benchmarks do Gemma 2 27B and Nvidia Llama 3.3 Nemotron Super 49b v1.5 share?
12 benchmarks have published results for both models. Gemma 2 27B has 34 scored results on Noometry and Nvidia Llama 3.3 Nemotron Super 49b v1.5 has 12.