Model comparison
Nemotron 4 340b Instruct vs Qwen2-72B
Nemotron 4 340b Instruct is the stronger model overall, scoring 35.3 to 29.5 on the Noometry Index.
Last verified . 17 shared benchmarks.
NVIDIA
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. Nemotron 4 340b Instruct scores higher in 8 categories and Qwen2-72B in 0 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Nemotron 4 340b Instruct leads 31.4 to 21.2.
Side by side
| Nemotron 4 340b Instruct | Qwen2-72B | |
|---|---|---|
| Provider | NVIDIA | Alibaba (Qwen) |
| Noometry Index | 35.3 | 29.5 |
| Released | 2024-06-14 | 2024-06-07 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 17 | 26 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Nemotron 4 340b Instruct leads
Nemotron 4 340b Instruct: 34.6 (#223), Qwen2-72B: 28.7 (#303)
| Benchmark | Nemotron 4 340b Instruct | Qwen2-72B |
|---|---|---|
| LMArena Coding | 1209 | 1196 |
| WeirdML | — | 11.3% |
| BigCodeBench Instruct | — | 38.5% |
| BigCodeBench Complete | — | 54% |
Agentic & Tool Use Not comparable
Nemotron 4 340b Instruct: —, Qwen2-72B: 16.9 (#138)
| Benchmark | Nemotron 4 340b Instruct | Qwen2-72B |
|---|---|---|
| TheAgentCompany | — | 1.1% |
| METR Time Horizons | — | 29.9% |
Reasoning Too close to call
Nemotron 4 340b Instruct: 22.4 (#180), Qwen2-72B: 22.2 (#184)
| Benchmark | Nemotron 4 340b Instruct | Qwen2-72B |
|---|---|---|
| LMArena Hard Prompts | 1202 | 1191 |
| Epoch Capabilities Index | — | 125.27 |
Math Nemotron 4 340b Instruct leads
Nemotron 4 340b Instruct: 31.7 (#193), Qwen2-72B: 27.9 (#232)
| Benchmark | Nemotron 4 340b Instruct | Qwen2-72B |
|---|---|---|
| LMArena Math | 1216 | 1235 |
| MATH Level 5 | — | 39.1% |
Knowledge Nemotron 4 340b Instruct leads
Nemotron 4 340b Instruct: 31.4 (#212), Qwen2-72B: 21.2 (#270)
| Benchmark | Nemotron 4 340b Instruct | Qwen2-72B |
|---|---|---|
| LMArena Expert | 1171 | 1171 |
| GPQA Diamond | — | 40.8% |
| MMLU | — | 82.4% |
Multilingual Nemotron 4 340b Instruct leads
Nemotron 4 340b Instruct: 38.0 (#228), Qwen2-72B: 36.0 (#239)
| Benchmark | Nemotron 4 340b Instruct | Qwen2-72B |
|---|---|---|
| LMArena Non-English | 1206 | 1176 |
| LMArena Chinese | 1214 | 1240 |
| LMArena French | 1196 | 1169 |
| LMArena German | 1192 | 1151 |
| LMArena Japanese | 1128 | 1111 |
| LMArena Korean | 1148 | 1083 |
| LMArena Russian | 1219 | 1169 |
| LMArena Spanish | 1195 | 1168 |
Instruction Following Nemotron 4 340b Instruct leads
Nemotron 4 340b Instruct: 63.3 (#227), Qwen2-72B: 62.0 (#236)
| Benchmark | Nemotron 4 340b Instruct | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | 1203 | 1181 |
Long Context Too close to call
Nemotron 4 340b Instruct: 37.1 (#216), Qwen2-72B: 36.1 (#230)
| Benchmark | Nemotron 4 340b Instruct | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | 1225 | 1193 |
Writing & Preference Nemotron 4 340b Instruct leads
Nemotron 4 340b Instruct: 42.9 (#229), Qwen2-72B: 41.0 (#236)
| Benchmark | Nemotron 4 340b Instruct | Qwen2-72B |
|---|---|---|
| LMArena Text | 1225 | 1203 |
| LMArena Creative Writing | 1203 | 1181 |
| LMArena Multi-Turn | 1214 | 1195 |
Frequently asked questions
Is Nemotron 4 340b Instruct better than Qwen2-72B?
Nemotron 4 340b Instruct is the stronger model overall, scoring 35.3 to 29.5 on the Noometry Index.
Is Nemotron 4 340b Instruct or Qwen2-72B better for coding?
Nemotron 4 340b Instruct scores higher on coding benchmarks: 34.6 versus 28.7 in the Noometry coding category.
How many benchmarks do Nemotron 4 340b Instruct and Qwen2-72B share?
17 benchmarks have published results for both models. Nemotron 4 340b Instruct has 17 scored results on Noometry and Qwen2-72B has 26.