Model comparison
Nemotron 4 340b Instruct vs Qwen1.5-110B
Nemotron 4 340b Instruct is the stronger model overall, scoring 35.9 to 34.2 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 Qwen1.5-110B in 0 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Nemotron 4 340b Instruct leads 42.7 to 38.0.
Side by side
| Nemotron 4 340b Instruct | Qwen1.5-110B | |
|---|---|---|
| Provider | NVIDIA | Alibaba (Qwen) |
| Noometry Index | 35.9 | 34.2 |
| Released | 2024-06-14 | 2024-04-25 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 17 | 20 |
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: 35.2 (#228), Qwen1.5-110B: 33.0 (#264)
| Benchmark | Nemotron 4 340b Instruct | Qwen1.5-110B |
|---|---|---|
| LMArena Coding | 1209 | 1184 |
| BigCodeBench Instruct | — | 35% |
| BigCodeBench Complete | — | 44.4% |
Reasoning Too close to call
Nemotron 4 340b Instruct: 23.4 (#178), Qwen1.5-110B: 22.7 (#189)
| Benchmark | Nemotron 4 340b Instruct | Qwen1.5-110B |
|---|---|---|
| LMArena Hard Prompts | 1202 | 1168 |
| ForecastBench | — | 57.7 |
Math Too close to call
Nemotron 4 340b Instruct: 34.3 (#195), Qwen1.5-110B: 33.7 (#201)
| Benchmark | Nemotron 4 340b Instruct | Qwen1.5-110B |
|---|---|---|
| LMArena Math | 1216 | 1185 |
Knowledge Too close to call
Nemotron 4 340b Instruct: 32.0 (#216), Qwen1.5-110B: 31.2 (#219)
| Benchmark | Nemotron 4 340b Instruct | Qwen1.5-110B |
|---|---|---|
| LMArena Expert | 1171 | 1144 |
Multilingual Nemotron 4 340b Instruct leads
Nemotron 4 340b Instruct: 37.9 (#233), Qwen1.5-110B: 33.6 (#250)
| Benchmark | Nemotron 4 340b Instruct | Qwen1.5-110B |
|---|---|---|
| LMArena Non-English | 1206 | 1142 |
| LMArena Chinese | 1214 | 1206 |
| LMArena French | 1197 | 1151 |
| LMArena German | 1192 | 1123 |
| LMArena Japanese | 1128 | 1074 |
| LMArena Korean | 1148 | 1044 |
| LMArena Russian | 1219 | 1118 |
| LMArena Spanish | 1195 | 1142 |
Instruction Following Nemotron 4 340b Instruct leads
Nemotron 4 340b Instruct: 63.1 (#232), Qwen1.5-110B: 60.3 (#252)
| Benchmark | Nemotron 4 340b Instruct | Qwen1.5-110B |
|---|---|---|
| LMArena Instruction Following | 1203 | 1158 |
Long Context Nemotron 4 340b Instruct leads
Nemotron 4 340b Instruct: 37.1 (#221), Qwen1.5-110B: 35.1 (#242)
| Benchmark | Nemotron 4 340b Instruct | Qwen1.5-110B |
|---|---|---|
| LMArena Longer Query | 1225 | 1157 |
Writing & Preference Nemotron 4 340b Instruct leads
Nemotron 4 340b Instruct: 42.7 (#233), Qwen1.5-110B: 38.0 (#255)
| Benchmark | Nemotron 4 340b Instruct | Qwen1.5-110B |
|---|---|---|
| LMArena Text | 1225 | 1175 |
| LMArena Creative Writing | 1203 | 1148 |
| LMArena Multi-Turn | 1214 | 1160 |
Frequently asked questions
Is Nemotron 4 340b Instruct better than Qwen1.5-110B?
Nemotron 4 340b Instruct is the stronger model overall, scoring 35.9 to 34.2 on the Noometry Index.
Is Nemotron 4 340b Instruct or Qwen1.5-110B better for coding?
Nemotron 4 340b Instruct scores higher on coding benchmarks: 35.2 versus 33.0 in the Noometry coding category.
How many benchmarks do Nemotron 4 340b Instruct and Qwen1.5-110B share?
17 benchmarks have published results for both models. Nemotron 4 340b Instruct has 17 scored results on Noometry and Qwen1.5-110B has 20.