Model comparison
Nemotron 3 Super vs Qwen2.5 7B Instruct
Nemotron 3 Super is the stronger model overall, scoring 40.1 to 29.0 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 12.6.
- Nemotron 3 Super is cheaper at $0.08 / $0.45 per million input/output tokens, against $0.17 / $0.70 for Qwen2.5 7B Instruct.
- Nemotron 3 Super accepts more context: 262K tokens versus 131K.
Side by side
| Nemotron 3 Super | Qwen2.5 7B Instruct | |
|---|---|---|
| Provider | NVIDIA | Alibaba (Qwen) |
| Noometry Index | 40.1 | 29.0 |
| Released | 2026-03-11 | 2024-09 |
| Weights | Open | Open |
| Context window | 262K | 131K |
| Max output | 131K | 8K |
| Input $ / M tokens | $0.08 | $0.17 |
| Output $ / M tokens | $0.45 | $0.70 |
| Results tracked | 21 | 15 |
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), Qwen2.5 7B Instruct: 36.5 (#208)
| Benchmark | Nemotron 3 Super | Qwen2.5 7B Instruct |
|---|---|---|
| SciCode | 36% | — |
| WeirdML | 38% | — |
| BigCodeBench Instruct | — | 37.6% |
| LMArena Coding | 1403 | — |
| BigCodeBench Complete | — | 46.1% |
| ALE-Bench | 213.9 | — |
Agentic & Tool Use Not comparable
Nemotron 3 Super: —, Qwen2.5 7B Instruct: 23.8 (#124)
| Benchmark | Nemotron 3 Super | Qwen2.5 7B Instruct |
|---|---|---|
| BALROG | — | 7.8% |
Reasoning Nemotron 3 Super leads
Nemotron 3 Super: 18.7 (#276), Qwen2.5 7B Instruct: 14.8 (#322)
| Benchmark | Nemotron 3 Super | Qwen2.5 7B Instruct |
|---|---|---|
| NYT Connections (extended) | 15.4% | — |
| CritPt | 3.1% | — |
| Chess Puzzles | — | 0% |
| LMArena Hard Prompts | 1386 | — |
| DTBench | — | 47.7% |
| LMCA | — | 6.4% |
| Epoch Capabilities Index | — | 118.51 |
Math Nemotron 3 Super leads
Nemotron 3 Super: 39.6 (#101), Qwen2.5 7B Instruct: 12.6 (#306)
| Benchmark | Nemotron 3 Super | Qwen2.5 7B Instruct |
|---|---|---|
| MathArena Final-Answer Competitions | 60.4% | — |
| OTIS Mock AIME 2024-2025 | — | 2.5% |
| Omni-MATH | — | 29.4% |
| LMArena Math | 1380 | — |
Knowledge Nemotron 3 Super leads
Nemotron 3 Super: 38.9 (#139), Qwen2.5 7B Instruct: 17.0 (#286)
| Benchmark | Nemotron 3 Super | Qwen2.5 7B Instruct |
|---|---|---|
| GPQA Diamond | — | 35.5% |
| MMLU-Pro | — | 53.9% |
| GPQA (HELM) | — | 34.1% |
| LMArena Expert | 1398 | — |
| MMLU | — | 72.9% |
Multilingual Not comparable
Nemotron 3 Super: 48.4 (#144), Qwen2.5 7B Instruct: —
| Benchmark | Nemotron 3 Super | Qwen2.5 7B Instruct |
|---|---|---|
| LMArena Non-English | 1355 | — |
| LMArena Chinese | 1432 | — |
| LMArena French | 1405 | — |
| LMArena German | 1341 | — |
| LMArena Russian | 1336 | — |
| LMArena Spanish | 1417 | — |
Instruction Following Nemotron 3 Super leads
Nemotron 3 Super: 71.2 (#154), Qwen2.5 7B Instruct: 63.2 (#231)
| Benchmark | Nemotron 3 Super | Qwen2.5 7B Instruct |
|---|---|---|
| IFEval | — | 74.1% |
| LMArena Instruction Following | 1347 | — |
Long Context Not comparable
Nemotron 3 Super: 41.5 (#139), Qwen2.5 7B Instruct: —
| Benchmark | Nemotron 3 Super | Qwen2.5 7B Instruct |
|---|---|---|
| LMArena Longer Query | 1362 | — |
Writing & Preference Nemotron 3 Super leads
Nemotron 3 Super: 55.9 (#140), Qwen2.5 7B Instruct: 48.8 (#195)
| Benchmark | Nemotron 3 Super | Qwen2.5 7B Instruct |
|---|---|---|
| LMArena Text | 1378 | — |
| LMArena Creative Writing | 1317 | — |
| WildBench | — | 73.1% |
| LMArena Multi-Turn | 1369 | — |
Frequently asked questions
Is Nemotron 3 Super better than Qwen2.5 7B Instruct?
Nemotron 3 Super is the stronger model overall, scoring 40.1 to 29.0 on the Noometry Index.
Which is cheaper, Nemotron 3 Super or Qwen2.5 7B Instruct?
Nemotron 3 Super is cheaper. It lists at $0.08 per million input tokens and $0.45 per million output tokens; Qwen2.5 7B Instruct lists at $0.17 and $0.70.
Is Nemotron 3 Super or Qwen2.5 7B Instruct better for coding?
Nemotron 3 Super scores higher on coding benchmarks: 39.4 versus 36.5 in the Noometry coding category.
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 7B Instruct share?
0 benchmarks have published results for both models. Nemotron 3 Super has 21 scored results on Noometry and Qwen2.5 7B Instruct has 15.