Model comparison
Hy3 vs phi-3-medium 14B
Hy3 is the stronger model overall, scoring 44.2 to 29.7 on the Noometry Index.
Last verified . 0 shared benchmarks.
Tencent
MicrosoftSummary
- The widest gap is in knowledge, where Hy3 leads 40.8 to 9.1.
Side by side
| Hy3 | phi-3-medium 14B | |
|---|---|---|
| Provider | Tencent | Microsoft |
| Noometry Index | 44.2 | 29.7 |
| Released | 2026-07-06 | 2024-04-23 |
| Weights | Open | Open |
| Context window | 262K | — |
| Max output | 128K | — |
| Input $ / M tokens | $0.13 | — |
| Output $ / M tokens | $0.53 | — |
| Results tracked | 19 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy3 leads
Hy3: 46.8 (#63), phi-3-medium 14B: 36.8 (#201)
| Benchmark | Hy3 | phi-3-medium 14B |
|---|---|---|
| LMArena WebDev | 1508 | — |
| BigCodeBench Instruct | — | 37.6% |
| LMArena Coding | 1464 | — |
| BigCodeBench Complete | — | 48.7% |
Reasoning Not comparable
Hy3: 26.1 (#136), phi-3-medium 14B: —
| Benchmark | Hy3 | phi-3-medium 14B |
|---|---|---|
| NYT Connections (extended) | 41.2% | — |
| LMArena Hard Prompts | 1447 | — |
| Adversarial NLI | — | 55.8% |
| BIG-Bench Hard | — | 81.4% |
| Epoch Capabilities Index | — | 121.23 |
| HellaSwag | — | 82.4% |
| WinoGrande | — | 81.5% |
Math Hy3 leads
Hy3: 40.1 (#93), phi-3-medium 14B: 27.3 (#250)
| Benchmark | Hy3 | phi-3-medium 14B |
|---|---|---|
| LMArena Math | 1475 | — |
| MATH Level 5 | — | 17.6% |
Knowledge Hy3 leads
Hy3: 40.8 (#114), phi-3-medium 14B: 9.1 (#306)
| Benchmark | Hy3 | phi-3-medium 14B |
|---|---|---|
| GPQA Diamond | — | 27.6% |
| LMArena Expert | 1460 | — |
| ARC (AI2) Challenge | — | 91.6% |
| MMLU | — | 78% |
| OpenBookQA | — | 87.4% |
| TriviaQA | — | 73.9% |
Multilingual Not comparable
Hy3: 53.5 (#65), phi-3-medium 14B: —
| Benchmark | Hy3 | phi-3-medium 14B |
|---|---|---|
| LMArena Non-English | 1426 | — |
| LMArena Chinese | 1493 | — |
| LMArena French | 1461 | — |
| LMArena German | 1439 | — |
| LMArena Japanese | 1392 | — |
| LMArena Korean | 1395 | — |
| LMArena Russian | 1432 | — |
| LMArena Spanish | 1456 | — |
Instruction Following Not comparable
Hy3: 75.1 (#70), phi-3-medium 14B: —
| Benchmark | Hy3 | phi-3-medium 14B |
|---|---|---|
| LMArena Instruction Following | 1426 | — |
Long Context Not comparable
Hy3: 44.1 (#75), phi-3-medium 14B: —
| Benchmark | Hy3 | phi-3-medium 14B |
|---|---|---|
| LMArena Longer Query | 1442 | — |
Writing & Preference Not comparable
Hy3: 62.2 (#81), phi-3-medium 14B: —
| Benchmark | Hy3 | phi-3-medium 14B |
|---|---|---|
| LMArena Text | 1439 | — |
| LMArena Creative Writing | 1402 | — |
| LMArena Multi-Turn | 1436 | — |
Frequently asked questions
Is Hy3 better than phi-3-medium 14B?
Hy3 is the stronger model overall, scoring 44.2 to 29.7 on the Noometry Index.
Is Hy3 or phi-3-medium 14B better for coding?
Hy3 scores higher on coding benchmarks: 46.8 versus 36.8 in the Noometry coding category.
How many benchmarks do Hy3 and phi-3-medium 14B share?
0 benchmarks have published results for both models. Hy3 has 19 scored results on Noometry and phi-3-medium 14B has 13.