Model comparison
Nemotron 3 Ultra vs Qwen3.6 Plus
Qwen3.6 Plus is the stronger model overall, scoring 47.5 to 42.5 on the Noometry Index.
Last verified . 25 shared benchmarks.
NVIDIA
Alibaba (Qwen)Summary
- They share 25 benchmarks with published results for both. Nemotron 3 Ultra scores higher in 3 categories and Qwen3.6 Plus in 5 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.6 Plus leads 51.8 to 35.3.
- The biggest single-benchmark swing is DTBench: 90.1% for Nemotron 3 Ultra and 81.9% for Qwen3.6 Plus.
- Nemotron 3 Ultra is cheaper at $0.50 / $2.20 per million input/output tokens, against $0.50 / $3 for Qwen3.6 Plus.
- Qwen3.6 Plus accepts more context: 1M tokens versus 262K.
- Nemotron 3 Ultra has downloadable open weights; the other is API-only.
Side by side
| Nemotron 3 Ultra | Qwen3.6 Plus | |
|---|---|---|
| Provider | NVIDIA | Alibaba (Qwen) |
| Noometry Index | 42.5 | 47.5 |
| Released | 2026-06-04 | 2026-03-31 |
| Weights | Open | Proprietary |
| Context window | 262K | 1M |
| Max output | 128K | 66K |
| Input $ / M tokens | $0.50 | $0.50 |
| Output $ / M tokens | $2.20 | $3 |
| Results tracked | 30 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.6 Plus leads
Nemotron 3 Ultra: 38.1 (#182), Qwen3.6 Plus: 40.8 (#130)
| Benchmark | Nemotron 3 Ultra | Qwen3.6 Plus |
|---|---|---|
| SciCode | 40.3% | 40.7% |
| LMArena Coding | 1468 | 1467 |
| SWE-bench Verified | — | 57.9% |
| FrontierCode | 13.6% | — |
| LMArena WebDev | — | 1461 |
| WeirdML | 43.5% | — |
| ALE-Bench | — | 670.15 |
Agentic & Tool Use Not comparable
Nemotron 3 Ultra: 23.4 (#126), Qwen3.6 Plus: —
| Benchmark | Nemotron 3 Ultra | Qwen3.6 Plus |
|---|---|---|
| APEX-Agents | 22.7% | — |
| Vending-Bench 2 | — | 5,115 |
Reasoning Nemotron 3 Ultra leads
Nemotron 3 Ultra: 31.0 (#82), Qwen3.6 Plus: 29.3 (#93)
| Benchmark | Nemotron 3 Ultra | Qwen3.6 Plus |
|---|---|---|
| CritPt | 3.1% | 2.9% |
| Chess Puzzles | 12% | 17% |
| LMArena Hard Prompts | 1452 | 1449 |
| Mystery Game Puzzles | 20% | 12% |
| DTBench | 90.1% | 81.9% |
| LMCA | 36.9% | 33.1% |
| Epoch Capabilities Index | 146.17 | 147.65 |
| NYT Connections (extended) | — | 60.3% |
| Thematic Generalization | — | 59.5% |
Math Qwen3.6 Plus leads
Nemotron 3 Ultra: 35.3 (#187), Qwen3.6 Plus: 51.8 (#54)
| Benchmark | Nemotron 3 Ultra | Qwen3.6 Plus |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 86.7% | 93.3% |
| LMArena Math | 1457 | 1450 |
| FrontierMath (Tiers 1-3) | — | 38.2% |
| ProofBench | 2% | — |
| FrontierMath (Feb 2025 set) | — | 26.2% |
| FrontierMath Tier 4 (v1) | — | 8.3% |
Knowledge Qwen3.6 Plus leads
Nemotron 3 Ultra: 52.5 (#61), Qwen3.6 Plus: 56.1 (#45)
| Benchmark | Nemotron 3 Ultra | Qwen3.6 Plus |
|---|---|---|
| GPQA Diamond | 85.4% | 88.4% |
| LMArena Expert | 1472 | 1454 |
| SimpleQA Verified | — | 44.1% |
Multilingual Too close to call
Nemotron 3 Ultra: 53.5 (#64), Qwen3.6 Plus: 53.3 (#70)
| Benchmark | Nemotron 3 Ultra | Qwen3.6 Plus |
|---|---|---|
| LMArena Non-English | 1427 | 1424 |
| LMArena Chinese | 1497 | 1477 |
| LMArena French | 1472 | 1455 |
| LMArena German | 1471 | 1452 |
| LMArena Korean | 1386 | 1379 |
| LMArena Russian | 1417 | 1434 |
| LMArena Spanish | 1454 | 1432 |
| LMArena Japanese | — | 1389 |
Instruction Following Too close to call
Nemotron 3 Ultra: 74.7 (#88), Qwen3.6 Plus: 75.0 (#74)
| Benchmark | Nemotron 3 Ultra | Qwen3.6 Plus |
|---|---|---|
| LMArena Instruction Following | 1418 | 1425 |
Long Context Qwen3.6 Plus leads
Nemotron 3 Ultra: 43.9 (#81), Qwen3.6 Plus: 45.2 (#49)
| Benchmark | Nemotron 3 Ultra | Qwen3.6 Plus |
|---|---|---|
| LMArena Longer Query | 1437 | 1439 |
| CL-bench | — | 20.3% |
Writing & Preference Nemotron 3 Ultra leads
Nemotron 3 Ultra: 66.3 (#36), Qwen3.6 Plus: 62.2 (#82)
| Benchmark | Nemotron 3 Ultra | Qwen3.6 Plus |
|---|---|---|
| LMArena Text | 1445 | 1437 |
| LMArena Creative Writing | 1398 | 1404 |
| LMArena Multi-Turn | 1411 | 1438 |
| EQ-Bench Creative Writing | 1692 | — |
Frequently asked questions
Is Nemotron 3 Ultra better than Qwen3.6 Plus?
Qwen3.6 Plus is the stronger model overall, scoring 47.5 to 42.5 on the Noometry Index.
Which is cheaper, Nemotron 3 Ultra or Qwen3.6 Plus?
Nemotron 3 Ultra is cheaper. It lists at $0.50 per million input tokens and $2.20 per million output tokens; Qwen3.6 Plus lists at $0.50 and $3.
Is Nemotron 3 Ultra or Qwen3.6 Plus better for coding?
Qwen3.6 Plus scores higher on coding benchmarks: 40.8 versus 38.1 in the Noometry coding category.
Which has the bigger context window?
Qwen3.6 Plus does, with 1M tokens against 262K.
How many benchmarks do Nemotron 3 Ultra and Qwen3.6 Plus share?
25 benchmarks have published results for both models. Nemotron 3 Ultra has 30 scored results on Noometry and Qwen3.6 Plus has 37.