Model comparison
Nemotron 3 Super vs Qwen3-30B-A3B
Nemotron 3 Super is the stronger model overall, scoring 40.1 to 38.9 on the Noometry Index.
Last verified . 19 shared benchmarks.
NVIDIA
Alibaba (Qwen)Summary
- They share 19 benchmarks with published results for both. Nemotron 3 Super scores higher in 4 categories and Qwen3-30B-A3B in 4 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in long context, where Nemotron 3 Super leads 41.5 to 31.0.
- The biggest single-benchmark swing is MathArena Final-Answer Competitions: 60.4% for Nemotron 3 Super and 47.8% for Qwen3-30B-A3B.
- Nemotron 3 Super is cheaper at $0.08 / $0.45 per million input/output tokens, against $0.12 / $0.50 for Qwen3-30B-A3B.
- Nemotron 3 Super accepts more context: 262K tokens versus 41K.
Side by side
| Nemotron 3 Super | Qwen3-30B-A3B | |
|---|---|---|
| Provider | NVIDIA | Alibaba (Qwen) |
| Noometry Index | 40.1 | 38.9 |
| Released | 2026-03-11 | 2025-04-28 |
| Weights | Open | Open |
| Context window | 262K | 41K |
| Max output | 131K | 16K |
| Input $ / M tokens | $0.08 | $0.12 |
| Output $ / M tokens | $0.45 | $0.50 |
| Results tracked | 21 | 32 |
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), Qwen3-30B-A3B: 37.5 (#194)
| Benchmark | Nemotron 3 Super | Qwen3-30B-A3B |
|---|---|---|
| SciCode | 36% | 33.3% |
| WeirdML | 38% | 29.8% |
| LMArena Coding | 1403 | 1416 |
| ALE-Bench | 213.9 | — |
Agentic & Tool Use Not comparable
Nemotron 3 Super: —, Qwen3-30B-A3B: 29.8 (#82)
| Benchmark | Nemotron 3 Super | Qwen3-30B-A3B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 41.4% |
Reasoning Qwen3-30B-A3B leads
Nemotron 3 Super: 18.7 (#276), Qwen3-30B-A3B: 22.2 (#204)
| Benchmark | Nemotron 3 Super | Qwen3-30B-A3B |
|---|---|---|
| CritPt | 3.1% | 0.3% |
| LMArena Hard Prompts | 1386 | 1398 |
| Kagi LLM Benchmark | — | 54.9% |
| NYT Connections (extended) | 15.4% | — |
| Chess Puzzles | — | 8% |
| DTBench | — | 69.3% |
| LMCA | — | 22.4% |
| Epoch Capabilities Index | — | 139.63 |
Math Nemotron 3 Super leads
Nemotron 3 Super: 39.6 (#101), Qwen3-30B-A3B: 37.4 (#157)
| Benchmark | Nemotron 3 Super | Qwen3-30B-A3B |
|---|---|---|
| MathArena Final-Answer Competitions | 60.4% | 47.8% |
| LMArena Math | 1380 | 1394 |
| OTIS Mock AIME 2024-2025 | — | 70.3% |
Knowledge Qwen3-30B-A3B leads
Nemotron 3 Super: 38.9 (#139), Qwen3-30B-A3B: 41.8 (#105)
| Benchmark | Nemotron 3 Super | Qwen3-30B-A3B |
|---|---|---|
| LMArena Expert | 1398 | 1396 |
| GPQA Diamond | — | 70.1% |
| Confabulations | — | 12.3% |
Multilingual Qwen3-30B-A3B leads
Nemotron 3 Super: 48.4 (#144), Qwen3-30B-A3B: 49.5 (#132)
| Benchmark | Nemotron 3 Super | Qwen3-30B-A3B |
|---|---|---|
| LMArena Non-English | 1355 | 1372 |
| LMArena Chinese | 1432 | 1433 |
| LMArena French | 1405 | 1418 |
| LMArena German | 1341 | 1380 |
| LMArena Russian | 1336 | 1370 |
| LMArena Spanish | 1417 | 1404 |
| LMArena Japanese | — | 1337 |
| LMArena Korean | — | 1331 |
Instruction Following Too close to call
Nemotron 3 Super: 71.2 (#154), Qwen3-30B-A3B: 72.0 (#142)
| Benchmark | Nemotron 3 Super | Qwen3-30B-A3B |
|---|---|---|
| LMArena Instruction Following | 1347 | 1363 |
Long Context Nemotron 3 Super leads
Nemotron 3 Super: 41.5 (#139), Qwen3-30B-A3B: 31.0 (#283)
| Benchmark | Nemotron 3 Super | Qwen3-30B-A3B |
|---|---|---|
| LMArena Longer Query | 1362 | 1379 |
| Fiction.LiveBench | — | 40.6% |
Writing & Preference Too close to call
Nemotron 3 Super: 55.9 (#140), Qwen3-30B-A3B: 55.6 (#143)
| Benchmark | Nemotron 3 Super | Qwen3-30B-A3B |
|---|---|---|
| LMArena Text | 1378 | 1384 |
| LMArena Creative Writing | 1317 | 1317 |
| LMArena Multi-Turn | 1369 | 1378 |
| Short-Story Creative Writing | — | 75.3% |
Frequently asked questions
Is Nemotron 3 Super better than Qwen3-30B-A3B?
Nemotron 3 Super is the stronger model overall, scoring 40.1 to 38.9 on the Noometry Index.
Which is cheaper, Nemotron 3 Super or Qwen3-30B-A3B?
Nemotron 3 Super is cheaper. It lists at $0.08 per million input tokens and $0.45 per million output tokens; Qwen3-30B-A3B lists at $0.12 and $0.50.
Is Nemotron 3 Super or Qwen3-30B-A3B better for coding?
Nemotron 3 Super scores higher on coding benchmarks: 39.4 versus 37.5 in the Noometry coding category.
Which has the bigger context window?
Nemotron 3 Super does, with 262K tokens against 41K.
How many benchmarks do Nemotron 3 Super and Qwen3-30B-A3B share?
19 benchmarks have published results for both models. Nemotron 3 Super has 21 scored results on Noometry and Qwen3-30B-A3B has 32.