Model comparison
Hy4 preview vs Llama 3.1 Nemotron Ultra 253b v1
Hy4 preview is the stronger model overall, scoring 45.3 to 36.7 on the Noometry Index.
Last verified . 0 shared benchmarks.
Tencent
NVIDIASummary
- The widest gap is in math, where Hy4 preview leads 55.7 to 37.5.
Side by side
| Hy4 preview | Llama 3.1 Nemotron Ultra 253b v1 | |
|---|---|---|
| Provider | Tencent | NVIDIA |
| Noometry Index | 45.3 | 36.7 |
| Released | 2026-08-28 | — |
| Weights | Open | Open |
| Context window | 1.05M | — |
| Max output | 64K | — |
| Input $ / M tokens | $0.75 | — |
| Output $ / M tokens | $2.25 | — |
| Results tracked | 3 | 11 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy4 preview leads
Hy4 preview: 51.6 (#38), Llama 3.1 Nemotron Ultra 253b v1: 38.4 (#177)
| Benchmark | Hy4 preview | Llama 3.1 Nemotron Ultra 253b v1 |
|---|---|---|
| LMArena WebDev | 1632 | — |
| LMArena Coding | — | 1312 |
Agentic & Tool Use Not comparable
Hy4 preview: —, Llama 3.1 Nemotron Ultra 253b v1: 15.7 (#149)
| Benchmark | Hy4 preview | Llama 3.1 Nemotron Ultra 253b v1 |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 10% |
Reasoning Hy4 preview leads
Hy4 preview: 31.9 (#79), Llama 3.1 Nemotron Ultra 253b v1: 26.3 (#134)
| Benchmark | Hy4 preview | Llama 3.1 Nemotron Ultra 253b v1 |
|---|---|---|
| NYT Connections (extended) | 68.2% | — |
| LMArena Hard Prompts | — | 1316 |
Math Hy4 preview leads
Hy4 preview: 55.7 (#42), Llama 3.1 Nemotron Ultra 253b v1: 37.5 (#152)
| Benchmark | Hy4 preview | Llama 3.1 Nemotron Ultra 253b v1 |
|---|---|---|
| ProofBench | 75% | — |
| LMArena Math | — | 1360 |
Multilingual Not comparable
Hy4 preview: —, Llama 3.1 Nemotron Ultra 253b v1: 43.1 (#187)
| Benchmark | Hy4 preview | Llama 3.1 Nemotron Ultra 253b v1 |
|---|---|---|
| LMArena Non-English | — | 1282 |
| LMArena Russian | — | 1284 |
Instruction Following Not comparable
Hy4 preview: —, Llama 3.1 Nemotron Ultra 253b v1: 69.0 (#178)
| Benchmark | Hy4 preview | Llama 3.1 Nemotron Ultra 253b v1 |
|---|---|---|
| LMArena Instruction Following | — | 1308 |
Long Context Not comparable
Hy4 preview: —, Llama 3.1 Nemotron Ultra 253b v1: 39.5 (#177)
| Benchmark | Hy4 preview | Llama 3.1 Nemotron Ultra 253b v1 |
|---|---|---|
| LMArena Longer Query | — | 1299 |
Writing & Preference Not comparable
Hy4 preview: —, Llama 3.1 Nemotron Ultra 253b v1: 52.2 (#175)
| Benchmark | Hy4 preview | Llama 3.1 Nemotron Ultra 253b v1 |
|---|---|---|
| LMArena Text | — | 1320 |
| LMArena Creative Writing | — | 1314 |
| LMArena Multi-Turn | — | 1317 |
Frequently asked questions
Is Hy4 preview better than Llama 3.1 Nemotron Ultra 253b v1?
Hy4 preview is the stronger model overall, scoring 45.3 to 36.7 on the Noometry Index.
Is Hy4 preview or Llama 3.1 Nemotron Ultra 253b v1 better for coding?
Hy4 preview scores higher on coding benchmarks: 51.6 versus 38.4 in the Noometry coding category.
How many benchmarks do Hy4 preview and Llama 3.1 Nemotron Ultra 253b v1 share?
0 benchmarks have published results for both models. Hy4 preview has 3 scored results on Noometry and Llama 3.1 Nemotron Ultra 253b v1 has 11.