Model comparison
Gemma 2 27B vs Nemotron 4 340b Instruct
Nemotron 4 340b Instruct is the stronger model overall, scoring 35.9 to 29.4 on the Noometry Index.
Last verified . 17 shared benchmarks.
Google
NVIDIASummary
- They share 17 benchmarks with published results for both. Gemma 2 27B scores higher in 3 categories and Nemotron 4 340b Instruct in 5 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Nemotron 4 340b Instruct leads 34.3 to 10.7.
Side by side
| Gemma 2 27B | Nemotron 4 340b Instruct | |
|---|---|---|
| Provider | NVIDIA | |
| Noometry Index | 29.4 | 35.9 |
| Released | 2024-06-24 | 2024-06-14 |
| Weights | Open | Open |
| Context window | 8K | — |
| Max output | 2K | — |
| Input $ / M tokens | $0.65 | — |
| Output $ / M tokens | $0.65 | — |
| Results tracked | 34 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Nemotron 4 340b Instruct leads
Gemma 2 27B: 34.1 (#246), Nemotron 4 340b Instruct: 35.2 (#228)
| Benchmark | Gemma 2 27B | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Coding | 1211 | 1209 |
| BigCodeBench Instruct | 42.8% | — |
| LiveBench Coding | 36% | — |
| BigCodeBench Complete | 52.5% | — |
Reasoning Nemotron 4 340b Instruct leads
Gemma 2 27B: 15.3 (#315), Nemotron 4 340b Instruct: 23.4 (#178)
| Benchmark | Gemma 2 27B | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Hard Prompts | 1198 | 1202 |
| LiveBench Reasoning | 28.1% | — |
| DTBench | 48% | — |
| LiveBench Data Analysis | 47.9% | — |
| LMCA | 7.1% | — |
| Epoch Capabilities Index | 122.08 | — |
| LiveBench | 38.2% | — |
Math Nemotron 4 340b Instruct leads
Gemma 2 27B: 10.7 (#311), Nemotron 4 340b Instruct: 34.3 (#195)
| Benchmark | Gemma 2 27B | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Math | 1212 | 1216 |
| OTIS Mock AIME 2024-2025 | 1.4% | — |
| LiveBench Math | 26.5% | — |
| MATH Level 5 | 27.9% | — |
Knowledge Nemotron 4 340b Instruct leads
Gemma 2 27B: 19.0 (#280), Nemotron 4 340b Instruct: 32.0 (#216)
| Benchmark | Gemma 2 27B | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Expert | 1172 | 1171 |
| GPQA Diamond | 36.5% | — |
| Confabulations | 27.1% | — |
| MMLU | 75.7% | — |
Multilingual Too close to call
Gemma 2 27B: 38.6 (#226), Nemotron 4 340b Instruct: 37.9 (#233)
| Benchmark | Gemma 2 27B | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Non-English | 1217 | 1206 |
| LMArena Chinese | 1221 | 1214 |
| LMArena French | 1247 | 1197 |
| LMArena German | 1209 | 1192 |
| LMArena Japanese | 1175 | 1128 |
| LMArena Korean | 1174 | 1148 |
| LMArena Russian | 1234 | 1219 |
| LMArena Spanish | 1228 | 1195 |
Instruction Following Nemotron 4 340b Instruct leads
Gemma 2 27B: 60.5 (#249), Nemotron 4 340b Instruct: 63.1 (#232)
| Benchmark | Gemma 2 27B | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Instruction Following | 1206 | 1203 |
| LiveBench Instruction Following | 58.1% | — |
Long Context Too close to call
Gemma 2 27B: 37.3 (#218), Nemotron 4 340b Instruct: 37.1 (#221)
| Benchmark | Gemma 2 27B | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Longer Query | 1231 | 1225 |
Writing & Preference Gemma 2 27B leads
Gemma 2 27B: 44.2 (#225), Nemotron 4 340b Instruct: 42.7 (#233)
| Benchmark | Gemma 2 27B | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Text | 1231 | 1225 |
| LMArena Creative Writing | 1241 | 1203 |
| LMArena Multi-Turn | 1224 | 1214 |
| LiveBench Language | 32.6% | — |
Frequently asked questions
Is Gemma 2 27B better than Nemotron 4 340b Instruct?
Nemotron 4 340b Instruct is the stronger model overall, scoring 35.9 to 29.4 on the Noometry Index.
Is Gemma 2 27B or Nemotron 4 340b Instruct better for coding?
Nemotron 4 340b Instruct scores higher on coding benchmarks: 35.2 versus 34.1 in the Noometry coding category.
How many benchmarks do Gemma 2 27B and Nemotron 4 340b Instruct share?
17 benchmarks have published results for both models. Gemma 2 27B has 34 scored results on Noometry and Nemotron 4 340b Instruct has 17.