Model comparison
Hy3 vs Nemotron 3 Super
Hy3 is the stronger model overall, scoring 44.2 to 40.1 on the Noometry Index.
Last verified . 16 shared benchmarks.
Tencent
NVIDIASummary
- They share 16 benchmarks with published results for both. Hy3 scores higher in 8 categories and Nemotron 3 Super in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in coding, where Hy3 leads 46.8 to 39.4.
- The biggest single-benchmark swing is NYT Connections (extended): 41.2% for Hy3 and 15.4% for Nemotron 3 Super.
- Hy3 is cheaper at $0.0825 / $0.33 per million input/output tokens, against $0.08 / $0.45 for Nemotron 3 Super.
Side by side
| Hy3 | Nemotron 3 Super | |
|---|---|---|
| Provider | Tencent | NVIDIA |
| Noometry Index | 44.2 | 40.1 |
| Released | 2026-07-06 | 2026-03-11 |
| Weights | Open | Open |
| Context window | 262K | 262K |
| Max output | 128K | 131K |
| Input $ / M tokens | $0.0825 | $0.08 |
| Output $ / M tokens | $0.33 | $0.45 |
| Results tracked | 19 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy3 leads
Hy3: 46.8 (#63), Nemotron 3 Super: 39.4 (#158)
| Benchmark | Hy3 | Nemotron 3 Super |
|---|---|---|
| LMArena Coding | 1464 | 1403 |
| LMArena WebDev | 1508 | — |
| SciCode | — | 36% |
| WeirdML | — | 38% |
| ALE-Bench | — | 213.9 |
Reasoning Hy3 leads
Hy3: 26.1 (#136), Nemotron 3 Super: 18.7 (#276)
| Benchmark | Hy3 | Nemotron 3 Super |
|---|---|---|
| NYT Connections (extended) | 41.2% | 15.4% |
| LMArena Hard Prompts | 1447 | 1386 |
| CritPt | — | 3.1% |
Math Too close to call
Hy3: 40.1 (#93), Nemotron 3 Super: 39.6 (#101)
| Benchmark | Hy3 | Nemotron 3 Super |
|---|---|---|
| LMArena Math | 1475 | 1380 |
| MathArena Final-Answer Competitions | — | 60.4% |
Knowledge Hy3 leads
Hy3: 40.8 (#114), Nemotron 3 Super: 38.9 (#139)
| Benchmark | Hy3 | Nemotron 3 Super |
|---|---|---|
| LMArena Expert | 1460 | 1398 |
Multilingual Hy3 leads
Hy3: 53.5 (#65), Nemotron 3 Super: 48.4 (#144)
| Benchmark | Hy3 | Nemotron 3 Super |
|---|---|---|
| LMArena Non-English | 1426 | 1355 |
| LMArena Chinese | 1493 | 1432 |
| LMArena French | 1461 | 1405 |
| LMArena German | 1439 | 1341 |
| LMArena Russian | 1432 | 1336 |
| LMArena Spanish | 1456 | 1417 |
| LMArena Japanese | 1392 | — |
| LMArena Korean | 1395 | — |
Instruction Following Hy3 leads
Hy3: 75.1 (#70), Nemotron 3 Super: 71.2 (#154)
| Benchmark | Hy3 | Nemotron 3 Super |
|---|---|---|
| LMArena Instruction Following | 1426 | 1347 |
Long Context Hy3 leads
Hy3: 44.1 (#75), Nemotron 3 Super: 41.5 (#139)
| Benchmark | Hy3 | Nemotron 3 Super |
|---|---|---|
| LMArena Longer Query | 1442 | 1362 |
Writing & Preference Hy3 leads
Hy3: 62.2 (#81), Nemotron 3 Super: 55.9 (#140)
| Benchmark | Hy3 | Nemotron 3 Super |
|---|---|---|
| LMArena Text | 1439 | 1378 |
| LMArena Creative Writing | 1402 | 1317 |
| LMArena Multi-Turn | 1436 | 1369 |
Frequently asked questions
Is Hy3 better than Nemotron 3 Super?
Hy3 is the stronger model overall, scoring 44.2 to 40.1 on the Noometry Index.
Which is cheaper, Hy3 or Nemotron 3 Super?
Hy3 is cheaper. It lists at $0.0825 per million input tokens and $0.33 per million output tokens; Nemotron 3 Super lists at $0.08 and $0.45.
Is Hy3 or Nemotron 3 Super better for coding?
Hy3 scores higher on coding benchmarks: 46.8 versus 39.4 in the Noometry coding category.
Which has the bigger context window?
Both accept 262K tokens.
How many benchmarks do Hy3 and Nemotron 3 Super share?
16 benchmarks have published results for both models. Hy3 has 19 scored results on Noometry and Nemotron 3 Super has 21.