Model comparison
Nvidia Llama 3.3 Nemotron Super 49b v1.5 vs Qwen3-30B-A3B
Nvidia Llama 3.3 Nemotron Super 49b v1.5 is the stronger model overall, scoring 40.3 to 38.9 on the Noometry Index. Qwen3-30B-A3B costs 1.9× less per token, which makes it the better buy when Nvidia Llama 3.3 Nemotron Super 49b v1.5's lead doesn't matter for your workload.
Last verified . 12 shared benchmarks.
NVIDIA
Alibaba (Qwen)Summary
- They share 12 benchmarks with published results for both. Nvidia Llama 3.3 Nemotron Super 49b v1.5 scores higher in 4 categories and Qwen3-30B-A3B in 4 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in long context, where Nvidia Llama 3.3 Nemotron Super 49b v1.5 leads 40.0 to 31.0.
- Qwen3-30B-A3B is cheaper at $0.12 / $0.50 per million input/output tokens, against $0.40 / $0.40 for Nvidia Llama 3.3 Nemotron Super 49b v1.5.
- Nvidia Llama 3.3 Nemotron Super 49b v1.5 accepts more context: 131K tokens versus 41K.
Side by side
| Nvidia Llama 3.3 Nemotron Super 49b v1.5 | Qwen3-30B-A3B | |
|---|---|---|
| Provider | NVIDIA | Alibaba (Qwen) |
| Noometry Index | 40.3 | 38.9 |
| Released | 2025-07-25 | 2025-04-28 |
| Weights | Open | Open |
| Context window | 131K | 41K |
| Max output | 131K | 16K |
| Input $ / M tokens | $0.40 | $0.12 |
| Output $ / M tokens | $0.40 | $0.50 |
| Results tracked | 12 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Nvidia Llama 3.3 Nemotron Super 49b v1.5 leads
Nvidia Llama 3.3 Nemotron Super 49b v1.5: 39.8 (#154), Qwen3-30B-A3B: 37.5 (#194)
| Benchmark | Nvidia Llama 3.3 Nemotron Super 49b v1.5 | Qwen3-30B-A3B |
|---|---|---|
| LMArena Coding | 1355 | 1416 |
| SciCode | — | 33.3% |
| WeirdML | — | 29.8% |
Agentic & Tool Use Not comparable
Nvidia Llama 3.3 Nemotron Super 49b v1.5: —, Qwen3-30B-A3B: 29.8 (#82)
| Benchmark | Nvidia Llama 3.3 Nemotron Super 49b v1.5 | Qwen3-30B-A3B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 41.4% |
Reasoning Nvidia Llama 3.3 Nemotron Super 49b v1.5 leads
Nvidia Llama 3.3 Nemotron Super 49b v1.5: 26.8 (#128), Qwen3-30B-A3B: 22.2 (#204)
| Benchmark | Nvidia Llama 3.3 Nemotron Super 49b v1.5 | Qwen3-30B-A3B |
|---|---|---|
| LMArena Hard Prompts | 1336 | 1398 |
| Kagi LLM Benchmark | — | 54.9% |
| CritPt | — | 0.3% |
| Chess Puzzles | — | 8% |
| DTBench | — | 69.3% |
| LMCA | — | 22.4% |
| Epoch Capabilities Index | — | 139.63 |
Math Too close to call
Nvidia Llama 3.3 Nemotron Super 49b v1.5: 38.2 (#141), Qwen3-30B-A3B: 37.4 (#157)
| Benchmark | Nvidia Llama 3.3 Nemotron Super 49b v1.5 | Qwen3-30B-A3B |
|---|---|---|
| LMArena Math | 1392 | 1394 |
| MathArena Final-Answer Competitions | — | 47.8% |
| OTIS Mock AIME 2024-2025 | — | 70.3% |
Knowledge Qwen3-30B-A3B leads
Nvidia Llama 3.3 Nemotron Super 49b v1.5: 36.7 (#165), Qwen3-30B-A3B: 41.8 (#105)
| Benchmark | Nvidia Llama 3.3 Nemotron Super 49b v1.5 | Qwen3-30B-A3B |
|---|---|---|
| LMArena Expert | 1330 | 1396 |
| GPQA Diamond | — | 70.1% |
| Confabulations | — | 12.3% |
Multilingual Qwen3-30B-A3B leads
Nvidia Llama 3.3 Nemotron Super 49b v1.5: 45.5 (#168), Qwen3-30B-A3B: 49.5 (#132)
| Benchmark | Nvidia Llama 3.3 Nemotron Super 49b v1.5 | Qwen3-30B-A3B |
|---|---|---|
| LMArena Non-English | 1316 | 1372 |
| LMArena Japanese | 1300 | 1337 |
| LMArena Russian | 1332 | 1370 |
| LMArena Chinese | — | 1433 |
| LMArena French | — | 1418 |
| LMArena German | — | 1380 |
| LMArena Korean | — | 1331 |
| LMArena Spanish | — | 1404 |
Instruction Following Qwen3-30B-A3B leads
Nvidia Llama 3.3 Nemotron Super 49b v1.5: 68.6 (#188), Qwen3-30B-A3B: 72.0 (#142)
| Benchmark | Nvidia Llama 3.3 Nemotron Super 49b v1.5 | Qwen3-30B-A3B |
|---|---|---|
| LMArena Instruction Following | 1299 | 1363 |
Long Context Nvidia Llama 3.3 Nemotron Super 49b v1.5 leads
Nvidia Llama 3.3 Nemotron Super 49b v1.5: 40.0 (#164), Qwen3-30B-A3B: 31.0 (#283)
| Benchmark | Nvidia Llama 3.3 Nemotron Super 49b v1.5 | Qwen3-30B-A3B |
|---|---|---|
| LMArena Longer Query | 1315 | 1379 |
| Fiction.LiveBench | — | 40.6% |
Writing & Preference Qwen3-30B-A3B leads
Nvidia Llama 3.3 Nemotron Super 49b v1.5: 53.1 (#159), Qwen3-30B-A3B: 55.6 (#143)
| Benchmark | Nvidia Llama 3.3 Nemotron Super 49b v1.5 | Qwen3-30B-A3B |
|---|---|---|
| LMArena Text | 1338 | 1384 |
| LMArena Creative Writing | 1307 | 1317 |
| LMArena Multi-Turn | 1334 | 1378 |
| Short-Story Creative Writing | — | 75.3% |
Frequently asked questions
Is Nvidia Llama 3.3 Nemotron Super 49b v1.5 better than Qwen3-30B-A3B?
Nvidia Llama 3.3 Nemotron Super 49b v1.5 is the stronger model overall, scoring 40.3 to 38.9 on the Noometry Index. Qwen3-30B-A3B costs 1.9× less per token, which makes it the better buy when Nvidia Llama 3.3 Nemotron Super 49b v1.5's lead doesn't matter for your workload.
Which is cheaper, Nvidia Llama 3.3 Nemotron Super 49b v1.5 or Qwen3-30B-A3B?
Qwen3-30B-A3B is cheaper. It lists at $0.12 per million input tokens and $0.50 per million output tokens; Nvidia Llama 3.3 Nemotron Super 49b v1.5 lists at $0.40 and $0.40.
Is Nvidia Llama 3.3 Nemotron Super 49b v1.5 or Qwen3-30B-A3B better for coding?
Nvidia Llama 3.3 Nemotron Super 49b v1.5 scores higher on coding benchmarks: 39.8 versus 37.5 in the Noometry coding category.
Which has the bigger context window?
Nvidia Llama 3.3 Nemotron Super 49b v1.5 does, with 131K tokens against 41K.
How many benchmarks do Nvidia Llama 3.3 Nemotron Super 49b v1.5 and Qwen3-30B-A3B share?
12 benchmarks have published results for both models. Nvidia Llama 3.3 Nemotron Super 49b v1.5 has 12 scored results on Noometry and Qwen3-30B-A3B has 32.