Model comparison
Nemotron 3 Super vs Qwen2-72B
Nemotron 3 Super is the stronger model overall, scoring 40.1 to 30.0 on the Noometry Index.
Last verified . 16 shared benchmarks.
NVIDIA
Alibaba (Qwen)Summary
- They share 16 benchmarks with published results for both. Nemotron 3 Super scores higher in 7 categories and Qwen2-72B in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Nemotron 3 Super leads 38.9 to 21.2.
- The biggest single-benchmark swing is WeirdML: 38% for Nemotron 3 Super and 11.3% for Qwen2-72B.
Side by side
| Nemotron 3 Super | Qwen2-72B | |
|---|---|---|
| Provider | NVIDIA | Alibaba (Qwen) |
| Noometry Index | 40.1 | 30.0 |
| Released | 2026-03-11 | 2024-06-07 |
| Weights | Open | Open |
| Context window | 262K | — |
| Max output | 131K | — |
| Input $ / M tokens | $0.08 | — |
| Output $ / M tokens | $0.45 | — |
| Results tracked | 21 | 26 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Nemotron 3 Super leads
Nemotron 3 Super: 39.4 (#158), Qwen2-72B: 29.1 (#310)
| Benchmark | Nemotron 3 Super | Qwen2-72B |
|---|---|---|
| WeirdML | 38% | 11.3% |
| LMArena Coding | 1403 | 1196 |
| SciCode | 36% | — |
| BigCodeBench Instruct | — | 38.5% |
| BigCodeBench Complete | — | 54% |
| ALE-Bench | 213.9 | — |
Agentic & Tool Use Not comparable
Nemotron 3 Super: —, Qwen2-72B: 17.0 (#146)
| Benchmark | Nemotron 3 Super | Qwen2-72B |
|---|---|---|
| TheAgentCompany | — | 1.1% |
| METR Time Horizons | — | 29.9% |
Reasoning Qwen2-72B leads
Nemotron 3 Super: 18.7 (#276), Qwen2-72B: 23.2 (#181)
| Benchmark | Nemotron 3 Super | Qwen2-72B |
|---|---|---|
| LMArena Hard Prompts | 1386 | 1191 |
| NYT Connections (extended) | 15.4% | — |
| CritPt | 3.1% | — |
| Epoch Capabilities Index | — | 125.28 |
Math Nemotron 3 Super leads
Nemotron 3 Super: 39.6 (#101), Qwen2-72B: 30.2 (#236)
| Benchmark | Nemotron 3 Super | Qwen2-72B |
|---|---|---|
| LMArena Math | 1380 | 1235 |
| MathArena Final-Answer Competitions | 60.4% | — |
| MATH Level 5 | — | 39.1% |
Knowledge Nemotron 3 Super leads
Nemotron 3 Super: 38.9 (#139), Qwen2-72B: 21.2 (#275)
| Benchmark | Nemotron 3 Super | Qwen2-72B |
|---|---|---|
| LMArena Expert | 1398 | 1171 |
| GPQA Diamond | — | 40.8% |
| MMLU | — | 82.4% |
Multilingual Nemotron 3 Super leads
Nemotron 3 Super: 48.4 (#144), Qwen2-72B: 35.9 (#244)
| Benchmark | Nemotron 3 Super | Qwen2-72B |
|---|---|---|
| LMArena Non-English | 1355 | 1176 |
| LMArena Chinese | 1432 | 1240 |
| LMArena French | 1405 | 1170 |
| LMArena German | 1341 | 1151 |
| LMArena Russian | 1336 | 1169 |
| LMArena Spanish | 1417 | 1169 |
| LMArena Japanese | — | 1111 |
| LMArena Korean | — | 1083 |
Instruction Following Nemotron 3 Super leads
Nemotron 3 Super: 71.2 (#154), Qwen2-72B: 61.7 (#241)
| Benchmark | Nemotron 3 Super | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | 1347 | 1181 |
Long Context Nemotron 3 Super leads
Nemotron 3 Super: 41.5 (#139), Qwen2-72B: 36.1 (#235)
| Benchmark | Nemotron 3 Super | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | 1362 | 1192 |
Writing & Preference Nemotron 3 Super leads
Nemotron 3 Super: 55.9 (#140), Qwen2-72B: 40.8 (#241)
| Benchmark | Nemotron 3 Super | Qwen2-72B |
|---|---|---|
| LMArena Text | 1378 | 1203 |
| LMArena Creative Writing | 1317 | 1181 |
| LMArena Multi-Turn | 1369 | 1196 |
Frequently asked questions
Is Nemotron 3 Super better than Qwen2-72B?
Nemotron 3 Super is the stronger model overall, scoring 40.1 to 30.0 on the Noometry Index.
Is Nemotron 3 Super or Qwen2-72B better for coding?
Nemotron 3 Super scores higher on coding benchmarks: 39.4 versus 29.1 in the Noometry coding category.
How many benchmarks do Nemotron 3 Super and Qwen2-72B share?
16 benchmarks have published results for both models. Nemotron 3 Super has 21 scored results on Noometry and Qwen2-72B has 26.