Model comparison
Hy3 vs Llama2 70b Steerlm Chat
Hy3 is the stronger model overall, scoring 44.2 to 31.8 on the Noometry Index.
Last verified . 9 shared benchmarks.
Tencent
NVIDIASummary
- They share 9 benchmarks with published results for both. Hy3 scores higher in 7 categories and Llama2 70b Steerlm Chat in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Hy3 leads 62.2 to 31.6.
Side by side
| Hy3 | Llama2 70b Steerlm Chat | |
|---|---|---|
| Provider | Tencent | NVIDIA |
| Noometry Index | 44.2 | 31.8 |
| Released | 2026-07-06 | — |
| Weights | Open | Open |
| Context window | 262K | — |
| Max output | 128K | — |
| Input $ / M tokens | $0.0825 | — |
| Output $ / M tokens | $0.33 | — |
| Results tracked | 19 | 9 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy3 leads
Hy3: 46.8 (#63), Llama2 70b Steerlm Chat: 29.9 (#300)
| Benchmark | Hy3 | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Coding | 1464 | 1025 |
| LMArena WebDev | 1508 | — |
Reasoning Hy3 leads
Hy3: 26.1 (#136), Llama2 70b Steerlm Chat: 20.0 (#246)
| Benchmark | Hy3 | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Hard Prompts | 1447 | 1047 |
| NYT Connections (extended) | 41.2% | — |
Math Hy3 leads
Hy3: 40.1 (#93), Llama2 70b Steerlm Chat: 31.3 (#226)
| Benchmark | Hy3 | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Math | 1475 | 1072 |
Knowledge Not comparable
Hy3: 40.8 (#114), Llama2 70b Steerlm Chat: —
| Benchmark | Hy3 | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Expert | 1460 | — |
Multilingual Hy3 leads
Hy3: 53.5 (#65), Llama2 70b Steerlm Chat: 28.8 (#270)
| Benchmark | Hy3 | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Non-English | 1426 | 1063 |
| LMArena Chinese | 1493 | — |
| LMArena French | 1461 | — |
| LMArena German | 1439 | — |
| LMArena Japanese | 1392 | — |
| LMArena Korean | 1395 | — |
| LMArena Russian | 1432 | — |
| LMArena Spanish | 1456 | — |
Instruction Following Hy3 leads
Hy3: 75.1 (#70), Llama2 70b Steerlm Chat: 54.2 (#279)
| Benchmark | Hy3 | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Instruction Following | 1426 | 1060 |
Long Context Hy3 leads
Hy3: 44.1 (#75), Llama2 70b Steerlm Chat: 30.4 (#288)
| Benchmark | Hy3 | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Longer Query | 1442 | 998 |
Writing & Preference Hy3 leads
Hy3: 62.2 (#81), Llama2 70b Steerlm Chat: 31.6 (#283)
| Benchmark | Hy3 | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Text | 1439 | 1098 |
| LMArena Creative Writing | 1402 | 1091 |
| LMArena Multi-Turn | 1436 | 1058 |
Frequently asked questions
Is Hy3 better than Llama2 70b Steerlm Chat?
Hy3 is the stronger model overall, scoring 44.2 to 31.8 on the Noometry Index.
Is Hy3 or Llama2 70b Steerlm Chat better for coding?
Hy3 scores higher on coding benchmarks: 46.8 versus 29.9 in the Noometry coding category.
How many benchmarks do Hy3 and Llama2 70b Steerlm Chat share?
9 benchmarks have published results for both models. Hy3 has 19 scored results on Noometry and Llama2 70b Steerlm Chat has 9.