Model comparison
Nemotron 3 Super vs Qwen3-Coder 480B-A35B Instruct
Nemotron 3 Super is the stronger model overall, scoring 40.1 to 38.1 on the Noometry Index.
Last verified . 17 shared benchmarks.
NVIDIA
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. Nemotron 3 Super scores higher in 5 categories and Qwen3-Coder 480B-A35B Instruct in 3 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen3-Coder 480B-A35B Instruct leads 25.5 to 18.7.
- Nemotron 3 Super is cheaper at $0.08 / $0.45 per million input/output tokens, against $1.50 / $7.50 for Qwen3-Coder 480B-A35B Instruct.
Side by side
| Nemotron 3 Super | Qwen3-Coder 480B-A35B Instruct | |
|---|---|---|
| Provider | NVIDIA | Alibaba (Qwen) |
| Noometry Index | 40.1 | 38.1 |
| Released | 2026-03-11 | 2025-04 |
| Weights | Open | Open |
| Context window | 262K | 262K |
| Max output | 131K | 66K |
| Input $ / M tokens | $0.08 | $1.50 |
| Output $ / M tokens | $0.45 | $7.50 |
| Results tracked | 21 | 25 |
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), Qwen3-Coder 480B-A35B Instruct: 35.5 (#223)
| Benchmark | Nemotron 3 Super | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| WeirdML | 38% | 41.2% |
| LMArena Coding | 1403 | 1412 |
| ALE-Bench | 213.9 | 461.45 |
| SWE-bench Verified (bash only) | — | 55.4% |
| LMArena WebDev | — | 1275 |
| SciCode | 36% | — |
| GSO | — | 4.9% |
| AlgoTune | — | 1.44 |
Agentic & Tool Use Not comparable
Nemotron 3 Super: —, Qwen3-Coder 480B-A35B Instruct: 23.9 (#123)
| Benchmark | Nemotron 3 Super | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| Terminal-Bench | — | 27.2% |
Reasoning Qwen3-Coder 480B-A35B Instruct leads
Nemotron 3 Super: 18.7 (#276), Qwen3-Coder 480B-A35B Instruct: 25.5 (#149)
| Benchmark | Nemotron 3 Super | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Hard Prompts | 1386 | 1372 |
| Kagi LLM Benchmark | — | 49.5% |
| NYT Connections (extended) | 15.4% | — |
| CritPt | 3.1% | — |
Math Nemotron 3 Super leads
Nemotron 3 Super: 39.6 (#101), Qwen3-Coder 480B-A35B Instruct: 37.6 (#150)
| Benchmark | Nemotron 3 Super | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Math | 1380 | 1365 |
| MathArena Final-Answer Competitions | 60.4% | — |
Knowledge Nemotron 3 Super leads
Nemotron 3 Super: 38.9 (#139), Qwen3-Coder 480B-A35B Instruct: 37.0 (#162)
| Benchmark | Nemotron 3 Super | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Expert | 1398 | 1338 |
Multilingual Too close to call
Nemotron 3 Super: 48.4 (#144), Qwen3-Coder 480B-A35B Instruct: 47.7 (#148)
| Benchmark | Nemotron 3 Super | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Non-English | 1355 | 1346 |
| LMArena Chinese | 1432 | 1357 |
| LMArena French | 1405 | 1398 |
| LMArena German | 1341 | 1325 |
| LMArena Russian | 1336 | 1366 |
| LMArena Spanish | 1417 | 1360 |
| LMArena Japanese | — | 1310 |
| LMArena Korean | — | 1305 |
Instruction Following Too close to call
Nemotron 3 Super: 71.2 (#154), Qwen3-Coder 480B-A35B Instruct: 71.6 (#147)
| Benchmark | Nemotron 3 Super | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Instruction Following | 1347 | 1355 |
Long Context Too close to call
Nemotron 3 Super: 41.5 (#139), Qwen3-Coder 480B-A35B Instruct: 42.0 (#131)
| Benchmark | Nemotron 3 Super | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Longer Query | 1362 | 1378 |
Writing & Preference Too close to call
Nemotron 3 Super: 55.9 (#140), Qwen3-Coder 480B-A35B Instruct: 55.3 (#147)
| Benchmark | Nemotron 3 Super | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Text | 1378 | 1357 |
| LMArena Creative Writing | 1317 | 1333 |
| LMArena Multi-Turn | 1369 | 1365 |
Frequently asked questions
Is Nemotron 3 Super better than Qwen3-Coder 480B-A35B Instruct?
Nemotron 3 Super is the stronger model overall, scoring 40.1 to 38.1 on the Noometry Index.
Which is cheaper, Nemotron 3 Super or Qwen3-Coder 480B-A35B Instruct?
Nemotron 3 Super is cheaper. It lists at $0.08 per million input tokens and $0.45 per million output tokens; Qwen3-Coder 480B-A35B Instruct lists at $1.50 and $7.50.
Is Nemotron 3 Super or Qwen3-Coder 480B-A35B Instruct better for coding?
Nemotron 3 Super scores higher on coding benchmarks: 39.4 versus 35.5 in the Noometry coding category.
Which has the bigger context window?
Both accept 262K tokens.
How many benchmarks do Nemotron 3 Super and Qwen3-Coder 480B-A35B Instruct share?
17 benchmarks have published results for both models. Nemotron 3 Super has 21 scored results on Noometry and Qwen3-Coder 480B-A35B Instruct has 25.