Model comparison
Nemotron 3 Super vs Qwen2.5-Coder-32B
Nemotron 3 Super is the stronger model overall, scoring 39.6 to 32.9 on the Noometry Index.
Last verified . 12 shared benchmarks.
NVIDIA
Alibaba (Qwen)Summary
- They share 12 benchmarks with published results for both. Nemotron 3 Super scores higher in 7 categories and Qwen2.5-Coder-32B in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where Nemotron 3 Super leads 38.9 to 22.4.
- Nemotron 3 Super is cheaper at $0.08 / $0.45 per million input/output tokens, against $0.66 / $1 for Qwen2.5-Coder-32B.
- Nemotron 3 Super accepts more context: 262K tokens versus 33K.
Side by side
| Nemotron 3 Super | Qwen2.5-Coder-32B | |
|---|---|---|
| Provider | NVIDIA | Alibaba (Qwen) |
| Noometry Index | 39.6 | 32.9 |
| Released | 2026-03-11 | 2024-09-18 |
| Weights | Open | Open |
| Context window | 262K | 33K |
| Max output | 131K | 29K |
| Input $ / M tokens | $0.08 | $0.66 |
| Output $ / M tokens | $0.45 | $1 |
| Results tracked | 21 | 31 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Nemotron 3 Super leads
Nemotron 3 Super: 38.9 (#153), Qwen2.5-Coder-32B: 22.4 (#328)
| Benchmark | Nemotron 3 Super | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Coding | 1403 | 1276 |
| SWE-bench Verified (bash only) | — | 9% |
| Aider Polyglot | — | 16.4% |
| SciCode | 36% | — |
| WeirdML | 38% | — |
| BigCodeBench Instruct | — | 49% |
| LiveBench Coding | — | 56.9% |
| BigCodeBench Complete | — | 58% |
| ALE-Bench | 213.9 | — |
| HumanEval+ | — | 87.2% |
| MBPP+ | — | 77% |
Reasoning Qwen2.5-Coder-32B leads
Nemotron 3 Super: 17.9 (#274), Qwen2.5-Coder-32B: 20.4 (#220)
| Benchmark | Nemotron 3 Super | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Hard Prompts | 1386 | 1251 |
| NYT Connections (extended) | 15.4% | — |
| CritPt | 3.1% | — |
| LiveBench Reasoning | — | 42.1% |
| LiveBench Data Analysis | — | 49.9% |
| Epoch Capabilities Index | — | 119.41 |
| HellaSwag | — | 83% |
| LiveBench | — | 46.2% |
| WinoGrande | — | 80.8% |
Math Nemotron 3 Super leads
Nemotron 3 Super: 37.6 (#95), Qwen2.5-Coder-32B: 30.8 (#203)
| Benchmark | Nemotron 3 Super | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Math | 1381 | 1251 |
| MathArena Final-Answer Competitions | 60.4% | — |
| LiveBench Math | — | 46.6% |
| GSM8K | — | 93% |
Knowledge Nemotron 3 Super leads
Nemotron 3 Super: 38.2 (#136), Qwen2.5-Coder-32B: 32.9 (#200)
| Benchmark | Nemotron 3 Super | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Expert | 1397 | 1221 |
| ARC (AI2) Challenge | — | 70.5% |
| MMLU | — | 79.1% |
Multilingual Nemotron 3 Super leads
Nemotron 3 Super: 48.6 (#139), Qwen2.5-Coder-32B: 38.0 (#230)
| Benchmark | Nemotron 3 Super | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Non-English | 1356 | 1205 |
| LMArena Chinese | 1430 | 1222 |
| LMArena Russian | 1336 | 1228 |
| LMArena French | 1404 | — |
| LMArena German | 1341 | — |
| LMArena Spanish | 1417 | — |
Instruction Following Nemotron 3 Super leads
Nemotron 3 Super: 71.4 (#149), Qwen2.5-Coder-32B: 61.6 (#240)
| Benchmark | Nemotron 3 Super | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Instruction Following | 1347 | 1223 |
| LiveBench Instruction Following | — | 58.7% |
Long Context Nemotron 3 Super leads
Nemotron 3 Super: 41.5 (#134), Qwen2.5-Coder-32B: 37.9 (#204)
| Benchmark | Nemotron 3 Super | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Longer Query | 1362 | 1251 |
Writing & Preference Nemotron 3 Super leads
Nemotron 3 Super: 56.1 (#135), Qwen2.5-Coder-32B: 41.8 (#235)
| Benchmark | Nemotron 3 Super | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Text | 1378 | 1230 |
| LMArena Creative Writing | 1317 | 1174 |
| LMArena Multi-Turn | 1369 | 1222 |
| LiveBench Language | — | 23.3% |
Frequently asked questions
Is Nemotron 3 Super better than Qwen2.5-Coder-32B?
Nemotron 3 Super is the stronger model overall, scoring 39.6 to 32.9 on the Noometry Index.
Which is cheaper, Nemotron 3 Super or Qwen2.5-Coder-32B?
Nemotron 3 Super is cheaper. It lists at $0.08 per million input tokens and $0.45 per million output tokens; Qwen2.5-Coder-32B lists at $0.66 and $1.
Is Nemotron 3 Super or Qwen2.5-Coder-32B better for coding?
Nemotron 3 Super scores higher on coding benchmarks: 38.9 versus 22.4 in the Noometry coding category.
Which has the bigger context window?
Nemotron 3 Super does, with 262K tokens against 33K.
How many benchmarks do Nemotron 3 Super and Qwen2.5-Coder-32B share?
12 benchmarks have published results for both models. Nemotron 3 Super has 21 scored results on Noometry and Qwen2.5-Coder-32B has 31.