Model comparison
Nemotron 3 Ultra vs Qwen3-4B
Nemotron 3 Ultra is the stronger model overall, scoring 42.5 to 31.9 on the Noometry Index.
Last verified . 3 shared benchmarks.
NVIDIA
Alibaba (Qwen)Summary
- They share 3 benchmarks with published results for both. Nemotron 3 Ultra scores higher in 3 categories and Qwen3-4B in 1 category; 4 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Nemotron 3 Ultra leads 52.5 to 33.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 86.7% for Nemotron 3 Ultra and 52.2% for Qwen3-4B.
Side by side
| Nemotron 3 Ultra | Qwen3-4B | |
|---|---|---|
| Provider | NVIDIA | Alibaba (Qwen) |
| Noometry Index | 42.5 | 31.9 |
| Released | 2026-06-04 | 2025-04-29 |
| Weights | Open | Open |
| Context window | 262K | — |
| Max output | 128K | — |
| Input $ / M tokens | $0.60 | — |
| Output $ / M tokens | $2.40 | — |
| Results tracked | 30 | 6 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Nemotron 3 Ultra: 38.1 (#182), Qwen3-4B: —
| Benchmark | Nemotron 3 Ultra | Qwen3-4B |
|---|---|---|
| FrontierCode | 13.6% | — |
| SciCode | 40.3% | — |
| WeirdML | 43.5% | — |
| LMArena Coding | 1468 | — |
Agentic & Tool Use Qwen3-4B leads
Nemotron 3 Ultra: 23.4 (#126), Qwen3-4B: 27.6 (#100)
| Benchmark | Nemotron 3 Ultra | Qwen3-4B |
|---|---|---|
| APEX-Agents | 22.7% | — |
| Berkeley Function Calling Leaderboard | — | 35.7% |
Reasoning Nemotron 3 Ultra leads
Nemotron 3 Ultra: 31.0 (#82), Qwen3-4B: 19.2 (#268)
| Benchmark | Nemotron 3 Ultra | Qwen3-4B |
|---|---|---|
| Chess Puzzles | 12% | 4% |
| CritPt | 3.1% | — |
| LMArena Hard Prompts | 1452 | — |
| Mystery Game Puzzles | 20% | — |
| DTBench | 90.1% | — |
| LMCA | 36.9% | — |
| Epoch Capabilities Index | 146.17 | — |
Math Nemotron 3 Ultra leads
Nemotron 3 Ultra: 35.3 (#187), Qwen3-4B: 29.7 (#240)
| Benchmark | Nemotron 3 Ultra | Qwen3-4B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 86.7% | 52.2% |
| MathArena Final-Answer Competitions | — | 38.5% |
| ProofBench | 2% | — |
| LMArena Math | 1457 | — |
Knowledge Nemotron 3 Ultra leads
Nemotron 3 Ultra: 52.5 (#61), Qwen3-4B: 33.0 (#208)
| Benchmark | Nemotron 3 Ultra | Qwen3-4B |
|---|---|---|
| GPQA Diamond | 85.4% | 52.3% |
| Vectara Hallucination Rate | — | 5.7% |
| LMArena Expert | 1472 | — |
Multilingual Not comparable
Nemotron 3 Ultra: 53.5 (#64), Qwen3-4B: —
| Benchmark | Nemotron 3 Ultra | Qwen3-4B |
|---|---|---|
| LMArena Non-English | 1427 | — |
| LMArena Chinese | 1497 | — |
| LMArena French | 1472 | — |
| LMArena German | 1471 | — |
| LMArena Korean | 1386 | — |
| LMArena Russian | 1417 | — |
| LMArena Spanish | 1454 | — |
Instruction Following Not comparable
Nemotron 3 Ultra: 74.7 (#88), Qwen3-4B: —
| Benchmark | Nemotron 3 Ultra | Qwen3-4B |
|---|---|---|
| LMArena Instruction Following | 1418 | — |
Long Context Not comparable
Nemotron 3 Ultra: 43.9 (#81), Qwen3-4B: —
| Benchmark | Nemotron 3 Ultra | Qwen3-4B |
|---|---|---|
| LMArena Longer Query | 1437 | — |
Writing & Preference Not comparable
Nemotron 3 Ultra: 66.3 (#36), Qwen3-4B: —
| Benchmark | Nemotron 3 Ultra | Qwen3-4B |
|---|---|---|
| LMArena Text | 1445 | — |
| LMArena Creative Writing | 1398 | — |
| EQ-Bench Creative Writing | 1692 | — |
| LMArena Multi-Turn | 1411 | — |
Frequently asked questions
Is Nemotron 3 Ultra better than Qwen3-4B?
Nemotron 3 Ultra is the stronger model overall, scoring 42.5 to 31.9 on the Noometry Index.
How many benchmarks do Nemotron 3 Ultra and Qwen3-4B share?
3 benchmarks have published results for both models. Nemotron 3 Ultra has 30 scored results on Noometry and Qwen3-4B has 6.