Model comparison
Hy3 vs Phi 3 Small 8k Instruct
Hy3 is the stronger model overall, scoring 44.2 to 29.3 on the Noometry Index.
Last verified . 17 shared benchmarks.
Tencent
MicrosoftSummary
- They share 17 benchmarks with published results for both. Hy3 scores higher in 8 categories and Phi 3 Small 8k Instruct in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Hy3 leads 62.2 to 31.1.
Side by side
| Hy3 | Phi 3 Small 8k Instruct | |
|---|---|---|
| Provider | Tencent | Microsoft |
| Noometry Index | 44.2 | 29.3 |
| Released | 2026-07-06 | 2024-04-23 |
| Weights | Open | Open |
| Context window | 262K | — |
| Max output | 128K | — |
| Input $ / M tokens | $0.0825 | — |
| Output $ / M tokens | $0.33 | — |
| Results tracked | 19 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy3 leads
Hy3: 46.8 (#63), Phi 3 Small 8k Instruct: 27.9 (#318)
| Benchmark | Hy3 | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Coding | 1464 | 1101 |
| LMArena WebDev | 1508 | — |
| LiveBench Coding | — | 20.3% |
Reasoning Hy3 leads
Hy3: 26.1 (#136), Phi 3 Small 8k Instruct: 14.8 (#323)
| Benchmark | Hy3 | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1447 | 1100 |
| NYT Connections (extended) | 41.2% | — |
| LiveBench Reasoning | — | 15.9% |
| LiveBench Data Analysis | — | 30.3% |
| Adversarial NLI | — | 58.1% |
| BIG-Bench Hard | — | 79.1% |
| HellaSwag | — | 77% |
| LiveBench | — | 24% |
| WinoGrande | — | 81.5% |
Math Hy3 leads
Hy3: 40.1 (#93), Phi 3 Small 8k Instruct: 27.6 (#248)
| Benchmark | Hy3 | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Math | 1475 | 1151 |
| LiveBench Math | — | 17.6% |
Knowledge Hy3 leads
Hy3: 40.8 (#114), Phi 3 Small 8k Instruct: 29.1 (#240)
| Benchmark | Hy3 | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Expert | 1460 | 1067 |
| ARC (AI2) Challenge | — | 90.7% |
| MMLU | — | 75.7% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 58.1% |
Multilingual Hy3 leads
Hy3: 53.5 (#65), Phi 3 Small 8k Instruct: 28.5 (#272)
| Benchmark | Hy3 | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Non-English | 1426 | 1058 |
| LMArena Chinese | 1493 | 1061 |
| LMArena French | 1461 | 1135 |
| LMArena German | 1439 | 1080 |
| LMArena Japanese | 1392 | 966 |
| LMArena Korean | 1395 | 894 |
| LMArena Russian | 1432 | 1111 |
| LMArena Spanish | 1456 | 1111 |
Instruction Following Hy3 leads
Hy3: 75.1 (#70), Phi 3 Small 8k Instruct: 51.9 (#292)
| Benchmark | Hy3 | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Instruction Following | 1426 | 1087 |
| LiveBench Instruction Following | — | 47.2% |
Long Context Hy3 leads
Hy3: 44.1 (#75), Phi 3 Small 8k Instruct: 33.0 (#267)
| Benchmark | Hy3 | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Longer Query | 1442 | 1088 |
Writing & Preference Hy3 leads
Hy3: 62.2 (#81), Phi 3 Small 8k Instruct: 31.1 (#284)
| Benchmark | Hy3 | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Text | 1439 | 1110 |
| LMArena Creative Writing | 1402 | 1083 |
| LMArena Multi-Turn | 1436 | 1068 |
| LiveBench Language | — | 12.9% |
Frequently asked questions
Is Hy3 better than Phi 3 Small 8k Instruct?
Hy3 is the stronger model overall, scoring 44.2 to 29.3 on the Noometry Index.
Is Hy3 or Phi 3 Small 8k Instruct better for coding?
Hy3 scores higher on coding benchmarks: 46.8 versus 27.9 in the Noometry coding category.
How many benchmarks do Hy3 and Phi 3 Small 8k Instruct share?
17 benchmarks have published results for both models. Hy3 has 19 scored results on Noometry and Phi 3 Small 8k Instruct has 32.