Model comparison
Gemini 1.0 Pro vs Nemotron 4 340b Instruct
Nemotron 4 340b Instruct is the stronger model overall, scoring 35.9 to 27.3 on the Noometry Index.
Last verified . 16 shared benchmarks.
Google
NVIDIASummary
- They share 16 benchmarks with published results for both. Gemini 1.0 Pro 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 math, where Nemotron 4 340b Instruct leads 34.3 to 9.3.
- Nemotron 4 340b Instruct has downloadable open weights; the other is API-only.
Side by side
| Gemini 1.0 Pro | Nemotron 4 340b Instruct | |
|---|---|---|
| Provider | NVIDIA | |
| Noometry Index | 27.3 | 35.9 |
| Released | 2023-12-13 | 2024-06-14 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 24 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Nemotron 4 340b Instruct leads
Gemini 1.0 Pro: 32.2 (#275), Nemotron 4 340b Instruct: 35.2 (#228)
| Benchmark | Gemini 1.0 Pro | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Coding | 1108 | 1209 |
| HumanEval+ | 55.5% | — |
| MBPP+ | 61.4% | — |
Reasoning Nemotron 4 340b Instruct leads
Gemini 1.0 Pro: 17.1 (#296), Nemotron 4 340b Instruct: 23.4 (#178)
| Benchmark | Gemini 1.0 Pro | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Hard Prompts | 1109 | 1202 |
| DTBench | 45.9% | — |
| Epoch Capabilities Index | 117.04 | — |
Math Nemotron 4 340b Instruct leads
Gemini 1.0 Pro: 9.3 (#321), Nemotron 4 340b Instruct: 34.3 (#195)
| Benchmark | Gemini 1.0 Pro | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Math | 1132 | 1216 |
| OTIS Mock AIME 2024-2025 | 1.1% | — |
| MATH Level 5 | 11.2% | — |
Knowledge Nemotron 4 340b Instruct leads
Gemini 1.0 Pro: 15.6 (#291), Nemotron 4 340b Instruct: 32.0 (#216)
| Benchmark | Gemini 1.0 Pro | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Expert | 1059 | 1171 |
| GPQA Diamond | 34% | — |
| MMLU | 70% | — |
Multilingual Nemotron 4 340b Instruct leads
Gemini 1.0 Pro: 33.4 (#252), Nemotron 4 340b Instruct: 37.9 (#233)
| Benchmark | Gemini 1.0 Pro | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Non-English | 1138 | 1206 |
| LMArena Chinese | 1124 | 1214 |
| LMArena French | 1145 | 1197 |
| LMArena German | 1125 | 1192 |
| LMArena Japanese | 1023 | 1128 |
| LMArena Russian | 1186 | 1219 |
| LMArena Spanish | 1119 | 1195 |
| LMArena Korean | — | 1148 |
Instruction Following Nemotron 4 340b Instruct leads
Gemini 1.0 Pro: 57.6 (#267), Nemotron 4 340b Instruct: 63.1 (#232)
| Benchmark | Gemini 1.0 Pro | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Instruction Following | 1114 | 1203 |
Long Context Nemotron 4 340b Instruct leads
Gemini 1.0 Pro: 34.3 (#249), Nemotron 4 340b Instruct: 37.1 (#221)
| Benchmark | Gemini 1.0 Pro | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Longer Query | 1132 | 1225 |
Writing & Preference Nemotron 4 340b Instruct leads
Gemini 1.0 Pro: 36.0 (#264), Nemotron 4 340b Instruct: 42.7 (#233)
| Benchmark | Gemini 1.0 Pro | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Text | 1149 | 1225 |
| LMArena Creative Writing | 1131 | 1203 |
| LMArena Multi-Turn | 1139 | 1214 |
Frequently asked questions
Is Gemini 1.0 Pro better than Nemotron 4 340b Instruct?
Nemotron 4 340b Instruct is the stronger model overall, scoring 35.9 to 27.3 on the Noometry Index.
Is Gemini 1.0 Pro or Nemotron 4 340b Instruct better for coding?
Nemotron 4 340b Instruct scores higher on coding benchmarks: 35.2 versus 32.2 in the Noometry coding category.
How many benchmarks do Gemini 1.0 Pro and Nemotron 4 340b Instruct share?
16 benchmarks have published results for both models. Gemini 1.0 Pro has 24 scored results on Noometry and Nemotron 4 340b Instruct has 17.