Model comparison
Nemotron 3 Super vs Qwen2.5 32B Instruct
Nemotron 3 Super is the stronger model overall, scoring 40.1 to 30.1 on the Noometry Index.
Last verified . 0 shared benchmarks.
NVIDIA
Alibaba (Qwen)Summary
- The widest gap is in math, where Nemotron 3 Super leads 39.6 to 16.2.
- Nemotron 3 Super is cheaper at $0.08 / $0.45 per million input/output tokens, against $0.70 / $2.80 for Qwen2.5 32B Instruct.
- Nemotron 3 Super accepts more context: 262K tokens versus 131K.
Side by side
| Nemotron 3 Super | Qwen2.5 32B Instruct | |
|---|---|---|
| Provider | NVIDIA | Alibaba (Qwen) |
| Noometry Index | 40.1 | 30.1 |
| Released | 2026-03-11 | 2024-09 |
| Weights | Open | Open |
| Context window | 262K | 131K |
| Max output | 131K | 8K |
| Input $ / M tokens | $0.08 | $0.70 |
| Output $ / M tokens | $0.45 | $2.80 |
| Results tracked | 21 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Nemotron 3 Super: 39.4 (#158), Qwen2.5 32B Instruct: 38.7 (#169)
| Benchmark | Nemotron 3 Super | Qwen2.5 32B Instruct |
|---|---|---|
| SciCode | 36% | — |
| WeirdML | 38% | — |
| BigCodeBench Instruct | — | 45% |
| LMArena Coding | 1403 | — |
| BigCodeBench Complete | — | 52.3% |
| ALE-Bench | 213.9 | — |
Reasoning Too close to call
Nemotron 3 Super: 18.7 (#276), Qwen2.5 32B Instruct: 19.2 (#266)
| Benchmark | Nemotron 3 Super | Qwen2.5 32B Instruct |
|---|---|---|
| NYT Connections (extended) | 15.4% | — |
| CritPt | 3.1% | — |
| Chess Puzzles | — | 0% |
| LMArena Hard Prompts | 1386 | — |
| Epoch Capabilities Index | — | 128.52 |
Math Nemotron 3 Super leads
Nemotron 3 Super: 39.6 (#101), Qwen2.5 32B Instruct: 16.2 (#296)
| Benchmark | Nemotron 3 Super | Qwen2.5 32B Instruct |
|---|---|---|
| MathArena Final-Answer Competitions | 60.4% | — |
| OTIS Mock AIME 2024-2025 | — | 7.4% |
| LMArena Math | 1380 | — |
| MATH Level 5 | — | 56.1% |
Knowledge Nemotron 3 Super leads
Nemotron 3 Super: 38.9 (#139), Qwen2.5 32B Instruct: 24.9 (#266)
| Benchmark | Nemotron 3 Super | Qwen2.5 32B Instruct |
|---|---|---|
| GPQA Diamond | — | 46.1% |
| LMArena Expert | 1398 | — |
Multilingual Not comparable
Nemotron 3 Super: 48.4 (#144), Qwen2.5 32B Instruct: —
| Benchmark | Nemotron 3 Super | Qwen2.5 32B Instruct |
|---|---|---|
| LMArena Non-English | 1355 | — |
| LMArena Chinese | 1432 | — |
| LMArena French | 1405 | — |
| LMArena German | 1341 | — |
| LMArena Russian | 1336 | — |
| LMArena Spanish | 1417 | — |
Instruction Following Not comparable
Nemotron 3 Super: 71.2 (#154), Qwen2.5 32B Instruct: —
| Benchmark | Nemotron 3 Super | Qwen2.5 32B Instruct |
|---|---|---|
| LMArena Instruction Following | 1347 | — |
Long Context Not comparable
Nemotron 3 Super: 41.5 (#139), Qwen2.5 32B Instruct: —
| Benchmark | Nemotron 3 Super | Qwen2.5 32B Instruct |
|---|---|---|
| LMArena Longer Query | 1362 | — |
Writing & Preference Not comparable
Nemotron 3 Super: 55.9 (#140), Qwen2.5 32B Instruct: —
| Benchmark | Nemotron 3 Super | Qwen2.5 32B Instruct |
|---|---|---|
| LMArena Text | 1378 | — |
| LMArena Creative Writing | 1317 | — |
| LMArena Multi-Turn | 1369 | — |
Frequently asked questions
Is Nemotron 3 Super better than Qwen2.5 32B Instruct?
Nemotron 3 Super is the stronger model overall, scoring 40.1 to 30.1 on the Noometry Index.
Which is cheaper, Nemotron 3 Super or Qwen2.5 32B Instruct?
Nemotron 3 Super is cheaper. It lists at $0.08 per million input tokens and $0.45 per million output tokens; Qwen2.5 32B Instruct lists at $0.70 and $2.80.
Is Nemotron 3 Super or Qwen2.5 32B Instruct better for coding?
They score almost the same on coding (39.4 vs 38.7); test both on your own repository before choosing.
Which has the bigger context window?
Nemotron 3 Super does, with 262K tokens against 131K.
How many benchmarks do Nemotron 3 Super and Qwen2.5 32B Instruct share?
0 benchmarks have published results for both models. Nemotron 3 Super has 21 scored results on Noometry and Qwen2.5 32B Instruct has 7.