Model comparison
Hy3 vs Nemotron 3 Ultra
Hy3 is the stronger model overall, scoring 44.2 to 42.5 on the Noometry Index.
Last verified . 16 shared benchmarks.
Tencent
NVIDIASummary
- They share 16 benchmarks with published results for both. Hy3 scores higher in 4 categories and Nemotron 3 Ultra in 4 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Nemotron 3 Ultra leads 52.5 to 40.8.
- Hy3 is cheaper at $0.0825 / $0.33 per million input/output tokens, against $0.50 / $2.20 for Nemotron 3 Ultra.
Side by side
| Hy3 | Nemotron 3 Ultra | |
|---|---|---|
| Provider | Tencent | NVIDIA |
| Noometry Index | 44.2 | 42.5 |
| Released | 2026-07-06 | 2026-06-04 |
| Weights | Open | Open |
| Context window | 262K | 262K |
| Max output | 128K | 128K |
| Input $ / M tokens | $0.0825 | $0.50 |
| Output $ / M tokens | $0.33 | $2.20 |
| Results tracked | 19 | 30 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy3 leads
Hy3: 46.8 (#63), Nemotron 3 Ultra: 38.1 (#182)
| Benchmark | Hy3 | Nemotron 3 Ultra |
|---|---|---|
| LMArena Coding | 1464 | 1468 |
| FrontierCode | — | 13.6% |
| LMArena WebDev | 1508 | — |
| SciCode | — | 40.3% |
| WeirdML | — | 43.5% |
Agentic & Tool Use Not comparable
Hy3: —, Nemotron 3 Ultra: 23.4 (#126)
| Benchmark | Hy3 | Nemotron 3 Ultra |
|---|---|---|
| APEX-Agents | — | 22.7% |
Reasoning Nemotron 3 Ultra leads
Hy3: 26.1 (#136), Nemotron 3 Ultra: 31.0 (#82)
| Benchmark | Hy3 | Nemotron 3 Ultra |
|---|---|---|
| LMArena Hard Prompts | 1447 | 1452 |
| NYT Connections (extended) | 41.2% | — |
| CritPt | — | 3.1% |
| Chess Puzzles | — | 12% |
| Mystery Game Puzzles | — | 20% |
| DTBench | — | 90.1% |
| LMCA | — | 36.9% |
| Epoch Capabilities Index | — | 146.17 |
Math Hy3 leads
Hy3: 40.1 (#93), Nemotron 3 Ultra: 35.3 (#187)
| Benchmark | Hy3 | Nemotron 3 Ultra |
|---|---|---|
| LMArena Math | 1475 | 1457 |
| OTIS Mock AIME 2024-2025 | — | 86.7% |
| ProofBench | — | 2% |
Knowledge Nemotron 3 Ultra leads
Hy3: 40.8 (#114), Nemotron 3 Ultra: 52.5 (#61)
| Benchmark | Hy3 | Nemotron 3 Ultra |
|---|---|---|
| LMArena Expert | 1460 | 1472 |
| GPQA Diamond | — | 85.4% |
Multilingual Too close to call
Hy3: 53.5 (#65), Nemotron 3 Ultra: 53.5 (#64)
| Benchmark | Hy3 | Nemotron 3 Ultra |
|---|---|---|
| LMArena Non-English | 1426 | 1427 |
| LMArena Chinese | 1493 | 1497 |
| LMArena French | 1461 | 1472 |
| LMArena German | 1439 | 1471 |
| LMArena Korean | 1395 | 1386 |
| LMArena Russian | 1432 | 1417 |
| LMArena Spanish | 1456 | 1454 |
| LMArena Japanese | 1392 | — |
Instruction Following Too close to call
Hy3: 75.1 (#70), Nemotron 3 Ultra: 74.7 (#88)
| Benchmark | Hy3 | Nemotron 3 Ultra |
|---|---|---|
| LMArena Instruction Following | 1426 | 1418 |
Long Context Too close to call
Hy3: 44.1 (#75), Nemotron 3 Ultra: 43.9 (#81)
| Benchmark | Hy3 | Nemotron 3 Ultra |
|---|---|---|
| LMArena Longer Query | 1442 | 1437 |
Writing & Preference Nemotron 3 Ultra leads
Hy3: 62.2 (#81), Nemotron 3 Ultra: 66.3 (#36)
| Benchmark | Hy3 | Nemotron 3 Ultra |
|---|---|---|
| LMArena Text | 1439 | 1445 |
| LMArena Creative Writing | 1402 | 1398 |
| LMArena Multi-Turn | 1436 | 1411 |
| EQ-Bench Creative Writing | — | 1692 |
Frequently asked questions
Is Hy3 better than Nemotron 3 Ultra?
Hy3 is the stronger model overall, scoring 44.2 to 42.5 on the Noometry Index.
Which is cheaper, Hy3 or Nemotron 3 Ultra?
Hy3 is cheaper. It lists at $0.0825 per million input tokens and $0.33 per million output tokens; Nemotron 3 Ultra lists at $0.50 and $2.20.
Is Hy3 or Nemotron 3 Ultra better for coding?
Hy3 scores higher on coding benchmarks: 46.8 versus 38.1 in the Noometry coding category.
Which has the bigger context window?
Both accept 262K tokens.
How many benchmarks do Hy3 and Nemotron 3 Ultra share?
16 benchmarks have published results for both models. Hy3 has 19 scored results on Noometry and Nemotron 3 Ultra has 30.