Model comparison
Nemotron 3 Super vs Qwen3.5 122B-A10B
Qwen3.5 122B-A10B is the stronger model overall, scoring 42.1 to 40.1 on the Noometry Index. Nemotron 3 Super costs 6.4× less per token, which makes it the better buy when Qwen3.5 122B-A10B's lead doesn't matter for your workload.
Last verified . 18 shared benchmarks.
NVIDIA
Alibaba (Qwen)Summary
- They share 18 benchmarks with published results for both. Nemotron 3 Super scores higher in 3 categories and Qwen3.5 122B-A10B in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen3.5 122B-A10B leads 27.2 to 18.7.
- The biggest single-benchmark swing is NYT Connections (extended): 15.4% for Nemotron 3 Super and 51.7% for Qwen3.5 122B-A10B.
- Nemotron 3 Super is cheaper at $0.08 / $0.45 per million input/output tokens, against $0.40 / $3.20 for Qwen3.5 122B-A10B.
Side by side
| Nemotron 3 Super | Qwen3.5 122B-A10B | |
|---|---|---|
| Provider | NVIDIA | Alibaba (Qwen) |
| Noometry Index | 40.1 | 42.1 |
| Released | 2026-03-11 | 2026-02-23 |
| Weights | Open | Open |
| Context window | 262K | 262K |
| Max output | 131K | 66K |
| Input $ / M tokens | $0.08 | $0.40 |
| Output $ / M tokens | $0.45 | $3.20 |
| Results tracked | 21 | 27 |
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), Qwen3.5 122B-A10B: 39.1 (#162)
| Benchmark | Nemotron 3 Super | Qwen3.5 122B-A10B |
|---|---|---|
| SciCode | 36% | 35.6% |
| LMArena Coding | 1403 | 1436 |
| LMArena WebDev | — | 1360 |
| WeirdML | 38% | — |
| ALE-Bench | 213.9 | — |
Reasoning Qwen3.5 122B-A10B leads
Nemotron 3 Super: 18.7 (#276), Qwen3.5 122B-A10B: 27.2 (#123)
| Benchmark | Nemotron 3 Super | Qwen3.5 122B-A10B |
|---|---|---|
| NYT Connections (extended) | 15.4% | 51.7% |
| CritPt | 3.1% | 0.9% |
| LMArena Hard Prompts | 1386 | 1421 |
| Thematic Generalization | — | 51.2% |
| Mystery Game Puzzles | — | 17% |
| DTBench | — | 84.3% |
| LMCA | — | 32.2% |
Math Too close to call
Nemotron 3 Super: 39.6 (#101), Qwen3.5 122B-A10B: 39.1 (#112)
| Benchmark | Nemotron 3 Super | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Math | 1380 | 1432 |
| MathArena Final-Answer Competitions | 60.4% | — |
Knowledge Too close to call
Nemotron 3 Super: 38.9 (#139), Qwen3.5 122B-A10B: 38.8 (#142)
| Benchmark | Nemotron 3 Super | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Expert | 1398 | 1432 |
| Vectara Hallucination Rate | — | 11.2% |
Multimodal Not comparable
Nemotron 3 Super: —, Qwen3.5 122B-A10B: 39.6 (#57)
| Benchmark | Nemotron 3 Super | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Vision | — | 1245 |
Multilingual Qwen3.5 122B-A10B leads
Nemotron 3 Super: 48.4 (#144), Qwen3.5 122B-A10B: 51.6 (#107)
| Benchmark | Nemotron 3 Super | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Non-English | 1355 | 1400 |
| LMArena Chinese | 1432 | 1462 |
| LMArena French | 1405 | 1442 |
| LMArena German | 1341 | 1426 |
| LMArena Russian | 1336 | 1400 |
| LMArena Spanish | 1417 | 1424 |
| LMArena Japanese | — | 1367 |
| LMArena Korean | — | 1352 |
Instruction Following Qwen3.5 122B-A10B leads
Nemotron 3 Super: 71.2 (#154), Qwen3.5 122B-A10B: 73.8 (#115)
| Benchmark | Nemotron 3 Super | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Instruction Following | 1347 | 1399 |
Long Context Qwen3.5 122B-A10B leads
Nemotron 3 Super: 41.5 (#139), Qwen3.5 122B-A10B: 43.0 (#109)
| Benchmark | Nemotron 3 Super | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Longer Query | 1362 | 1410 |
Writing & Preference Qwen3.5 122B-A10B leads
Nemotron 3 Super: 55.9 (#140), Qwen3.5 122B-A10B: 60.0 (#105)
| Benchmark | Nemotron 3 Super | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Text | 1378 | 1417 |
| LMArena Creative Writing | 1317 | 1368 |
| LMArena Multi-Turn | 1369 | 1416 |
Frequently asked questions
Is Nemotron 3 Super better than Qwen3.5 122B-A10B?
Qwen3.5 122B-A10B is the stronger model overall, scoring 42.1 to 40.1 on the Noometry Index. Nemotron 3 Super costs 6.4× less per token, which makes it the better buy when Qwen3.5 122B-A10B's lead doesn't matter for your workload.
Which is cheaper, Nemotron 3 Super or Qwen3.5 122B-A10B?
Nemotron 3 Super is cheaper. It lists at $0.08 per million input tokens and $0.45 per million output tokens; Qwen3.5 122B-A10B lists at $0.40 and $3.20.
Is Nemotron 3 Super or Qwen3.5 122B-A10B better for coding?
They score almost the same on coding (39.4 vs 39.1); test both on your own repository before choosing.
Which has the bigger context window?
Both accept 262K tokens.
How many benchmarks do Nemotron 3 Super and Qwen3.5 122B-A10B share?
18 benchmarks have published results for both models. Nemotron 3 Super has 21 scored results on Noometry and Qwen3.5 122B-A10B has 27.