Model comparison
Nemotron 3 Ultra vs Qwen2.5 Plus 1127
Nemotron 3 Ultra is the stronger model overall, scoring 44.7 to 38.1 on the Noometry Index.
Last verified . 13 shared benchmarks.
NVIDIA
Alibaba (Qwen)Summary
- They share 13 benchmarks with published results for both. Nemotron 3 Ultra scores higher in 7 categories and Qwen2.5 Plus 1127 in 1 category; 6 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Nemotron 3 Ultra leads 52.5 to 34.9.
- Nemotron 3 Ultra has downloadable open weights; the other is API-only.
Side by side
| Nemotron 3 Ultra | Qwen2.5 Plus 1127 | |
|---|---|---|
| Provider | NVIDIA | Alibaba (Qwen) |
| Noometry Index | 44.7 | 38.1 |
| Released | 2026-06-04 | — |
| Weights | Open | Proprietary |
| Context window | 262K | — |
| Max output | 128K | — |
| Input $ / M tokens | $0.60 | — |
| Output $ / M tokens | $2.40 | — |
| Results tracked | 29 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Nemotron 3 Ultra: 37.7 (#174), Qwen2.5 Plus 1127: 37.9 (#171)
| Benchmark | Nemotron 3 Ultra | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Coding | 1468 | 1314 |
| FrontierCode | 13.6% | — |
| SciCode | 40.3% | — |
| WeirdML | 43.5% | — |
Reasoning Nemotron 3 Ultra leads
Nemotron 3 Ultra: 30.3 (#78), Qwen2.5 Plus 1127: 24.8 (#139)
| Benchmark | Nemotron 3 Ultra | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Hard Prompts | 1452 | 1299 |
| CritPt | 3.1% | — |
| Chess Puzzles | 12% | — |
| Mystery Game Puzzles | 20% | — |
| DTBench | 90.1% | — |
| LMCA | 36.9% | — |
| Epoch Capabilities Index | 146.2 | — |
Math Too close to call
Nemotron 3 Ultra: 34.4 (#160), Qwen2.5 Plus 1127: 33.5 (#175)
| Benchmark | Nemotron 3 Ultra | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Math | 1456 | 1298 |
| OTIS Mock AIME 2024-2025 | 86.7% | — |
| ProofBench | 2% | — |
Knowledge Nemotron 3 Ultra leads
Nemotron 3 Ultra: 52.5 (#56), Qwen2.5 Plus 1127: 34.9 (#179)
| Benchmark | Nemotron 3 Ultra | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Expert | 1472 | 1289 |
| GPQA Diamond | 85.4% | — |
Multilingual Nemotron 3 Ultra leads
Nemotron 3 Ultra: 53.7 (#61), Qwen2.5 Plus 1127: 42.1 (#196)
| Benchmark | Nemotron 3 Ultra | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Non-English | 1427 | 1265 |
| LMArena Chinese | 1498 | 1314 |
| LMArena German | 1471 | 1231 |
| LMArena Russian | 1415 | 1271 |
| LMArena French | 1475 | — |
| LMArena Japanese | — | 1207 |
| LMArena Korean | 1387 | — |
| LMArena Spanish | 1452 | — |
Instruction Following Nemotron 3 Ultra leads
Nemotron 3 Ultra: 74.9 (#84), Qwen2.5 Plus 1127: 67.4 (#194)
| Benchmark | Nemotron 3 Ultra | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Instruction Following | 1417 | 1275 |
Long Context Nemotron 3 Ultra leads
Nemotron 3 Ultra: 43.9 (#77), Qwen2.5 Plus 1127: 39.2 (#180)
| Benchmark | Nemotron 3 Ultra | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Longer Query | 1437 | 1292 |
Writing & Preference Nemotron 3 Ultra leads
Nemotron 3 Ultra: 66.3 (#35), Qwen2.5 Plus 1127: 49.5 (#186)
| Benchmark | Nemotron 3 Ultra | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Text | 1444 | 1299 |
| LMArena Creative Writing | 1392 | 1262 |
| LMArena Multi-Turn | 1412 | 1299 |
| EQ-Bench Creative Writing | 1692 | — |
Frequently asked questions
Is Nemotron 3 Ultra better than Qwen2.5 Plus 1127?
Nemotron 3 Ultra is the stronger model overall, scoring 44.7 to 38.1 on the Noometry Index.
Is Nemotron 3 Ultra or Qwen2.5 Plus 1127 better for coding?
They score almost the same on coding (37.7 vs 37.9); test both on your own repository before choosing.
How many benchmarks do Nemotron 3 Ultra and Qwen2.5 Plus 1127 share?
13 benchmarks have published results for both models. Nemotron 3 Ultra has 29 scored results on Noometry and Qwen2.5 Plus 1127 has 14.