Model comparison
Hy3 vs Wizardlm 70b
Hy3 is the stronger model overall, scoring 44.2 to 33.0 on the Noometry Index.
Last verified . 12 shared benchmarks.
Tencent
MicrosoftSummary
- They share 12 benchmarks with published results for both. Hy3 scores higher in 7 categories and Wizardlm 70b in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Hy3 leads 62.2 to 34.8.
Side by side
| Hy3 | Wizardlm 70b | |
|---|---|---|
| Provider | Tencent | Microsoft |
| Noometry Index | 44.2 | 33.0 |
| 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 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy3 leads
Hy3: 46.8 (#63), Wizardlm 70b: 31.4 (#285)
| Benchmark | Hy3 | Wizardlm 70b |
|---|---|---|
| LMArena Coding | 1464 | 1081 |
| LMArena WebDev | 1508 | — |
Reasoning Hy3 leads
Hy3: 26.1 (#136), Wizardlm 70b: 20.7 (#234)
| Benchmark | Hy3 | Wizardlm 70b |
|---|---|---|
| LMArena Hard Prompts | 1447 | 1079 |
| NYT Connections (extended) | 41.2% | — |
Math Hy3 leads
Hy3: 40.1 (#93), Wizardlm 70b: 32.2 (#218)
| Benchmark | Hy3 | Wizardlm 70b |
|---|---|---|
| LMArena Math | 1475 | 1116 |
Knowledge Not comparable
Hy3: 40.8 (#114), Wizardlm 70b: —
| Benchmark | Hy3 | Wizardlm 70b |
|---|---|---|
| LMArena Expert | 1460 | — |
Multilingual Hy3 leads
Hy3: 53.5 (#65), Wizardlm 70b: 29.6 (#265)
| Benchmark | Hy3 | Wizardlm 70b |
|---|---|---|
| LMArena Non-English | 1426 | 1078 |
| LMArena Chinese | 1493 | 1052 |
| LMArena German | 1439 | 1083 |
| LMArena Russian | 1432 | 1155 |
| LMArena French | 1461 | — |
| LMArena Japanese | 1392 | — |
| LMArena Korean | 1395 | — |
| LMArena Spanish | 1456 | — |
Instruction Following Hy3 leads
Hy3: 75.1 (#70), Wizardlm 70b: 56.3 (#273)
| Benchmark | Hy3 | Wizardlm 70b |
|---|---|---|
| LMArena Instruction Following | 1426 | 1093 |
Long Context Hy3 leads
Hy3: 44.1 (#75), Wizardlm 70b: 33.3 (#263)
| Benchmark | Hy3 | Wizardlm 70b |
|---|---|---|
| LMArena Longer Query | 1442 | 1097 |
Writing & Preference Hy3 leads
Hy3: 62.2 (#81), Wizardlm 70b: 34.8 (#269)
| Benchmark | Hy3 | Wizardlm 70b |
|---|---|---|
| LMArena Text | 1439 | 1120 |
| LMArena Creative Writing | 1402 | 1149 |
| LMArena Multi-Turn | 1436 | 1108 |
Frequently asked questions
Is Hy3 better than Wizardlm 70b?
Hy3 is the stronger model overall, scoring 44.2 to 33.0 on the Noometry Index.
Is Hy3 or Wizardlm 70b better for coding?
Hy3 scores higher on coding benchmarks: 46.8 versus 31.4 in the Noometry coding category.
How many benchmarks do Hy3 and Wizardlm 70b share?
12 benchmarks have published results for both models. Hy3 has 19 scored results on Noometry and Wizardlm 70b has 12.