Model comparison
Gemma 7B vs Nemotron 4 340b Instruct
Nemotron 4 340b Instruct is the stronger model overall, scoring 35.9 to 30.0 on the Noometry Index.
Last verified . 13 shared benchmarks.
Google
NVIDIASummary
- They share 13 benchmarks with published results for both. Gemma 7B scores higher in 0 categories and Nemotron 4 340b Instruct in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Nemotron 4 340b Instruct leads 42.7 to 27.1.
Side by side
| Gemma 7B | Nemotron 4 340b Instruct | |
|---|---|---|
| Provider | NVIDIA | |
| Noometry Index | 30.0 | 35.9 |
| Released | 2024-02-21 | 2024-06-14 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 27 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Nemotron 4 340b Instruct leads
Gemma 7B: 30.5 (#294), Nemotron 4 340b Instruct: 35.2 (#228)
| Benchmark | Gemma 7B | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Coding | 1048 | 1209 |
| HumanEval+ | 28.7% | — |
| MBPP+ | 43.4% | — |
Reasoning Nemotron 4 340b Instruct leads
Gemma 7B: 19.9 (#249), Nemotron 4 340b Instruct: 23.4 (#178)
| Benchmark | Gemma 7B | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Hard Prompts | 1042 | 1202 |
| Adversarial NLI | 48.7% | — |
| BIG-Bench Hard | 55.1% | — |
| Epoch Capabilities Index | 111.99 | — |
| HellaSwag | 82.2% | — |
| PIQA | 81.2% | — |
| WinoGrande | 79% | — |
Math Nemotron 4 340b Instruct leads
Gemma 7B: 31.2 (#228), Nemotron 4 340b Instruct: 34.3 (#195)
| Benchmark | Gemma 7B | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Math | 1066 | 1216 |
| GSM8K | 46.4% | — |
Knowledge Nemotron 4 340b Instruct leads
Gemma 7B: 27.3 (#252), Nemotron 4 340b Instruct: 32.0 (#216)
| Benchmark | Gemma 7B | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Expert | 1001 | 1171 |
| ARC (AI2) Challenge | 78.3% | — |
| BoolQ | 83.2% | — |
| MMLU | 66.1% | — |
| OpenBookQA | 78.6% | — |
| TriviaQA | 72.3% | — |
Multilingual Nemotron 4 340b Instruct leads
Gemma 7B: 25.1 (#287), Nemotron 4 340b Instruct: 37.9 (#233)
| Benchmark | Gemma 7B | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Non-English | 999 | 1206 |
| LMArena Chinese | 1035 | 1214 |
| LMArena French | 1025 | 1197 |
| LMArena Russian | 993 | 1219 |
| LMArena German | — | 1192 |
| LMArena Japanese | — | 1128 |
| LMArena Korean | — | 1148 |
| LMArena Spanish | — | 1195 |
Instruction Following Nemotron 4 340b Instruct leads
Gemma 7B: 51.5 (#295), Nemotron 4 340b Instruct: 63.1 (#232)
| Benchmark | Gemma 7B | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Instruction Following | 1017 | 1203 |
Long Context Nemotron 4 340b Instruct leads
Gemma 7B: 31.1 (#282), Nemotron 4 340b Instruct: 37.1 (#221)
| Benchmark | Gemma 7B | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Longer Query | 1022 | 1225 |
Writing & Preference Nemotron 4 340b Instruct leads
Gemma 7B: 27.1 (#302), Nemotron 4 340b Instruct: 42.7 (#233)
| Benchmark | Gemma 7B | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Text | 1056 | 1225 |
| LMArena Creative Writing | 1024 | 1203 |
| LMArena Multi-Turn | 963 | 1214 |
Frequently asked questions
Is Gemma 7B better than Nemotron 4 340b Instruct?
Nemotron 4 340b Instruct is the stronger model overall, scoring 35.9 to 30.0 on the Noometry Index.
Is Gemma 7B or Nemotron 4 340b Instruct better for coding?
Nemotron 4 340b Instruct scores higher on coding benchmarks: 35.2 versus 30.5 in the Noometry coding category.
How many benchmarks do Gemma 7B and Nemotron 4 340b Instruct share?
13 benchmarks have published results for both models. Gemma 7B has 27 scored results on Noometry and Nemotron 4 340b Instruct has 17.