Model comparison
Hy4 preview vs Phi 3 Mini 128k Instruct
Hy4 preview is the stronger model overall, scoring 44.6 to 29.1 on the Noometry Index.
Last verified . 0 shared benchmarks.
Tencent
MicrosoftSummary
- The widest gap is in math, where Hy4 preview leads 54.5 to 29.2.
Side by side
| Hy4 preview | Phi 3 Mini 128k Instruct | |
|---|---|---|
| Provider | Tencent | Microsoft |
| Noometry Index | 44.6 | 29.1 |
| Released | 2026-08-28 | 2024-04-23 |
| Weights | Open | Open |
| Context window | 1.05M | — |
| Max output | 64K | — |
| Input $ / M tokens | $0.83 | — |
| Output $ / M tokens | $2.50 | — |
| Results tracked | 3 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy4 preview leads
Hy4 preview: 51.4 (#36), Phi 3 Mini 128k Instruct: 28.3 (#307)
| Benchmark | Hy4 preview | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena WebDev | 1633 | — |
| BigCodeBench Instruct | — | 29.6% |
| LMArena Coding | — | 1040 |
| BigCodeBench Complete | — | 40.6% |
Reasoning Hy4 preview leads
Hy4 preview: 30.6 (#75), Phi 3 Mini 128k Instruct: 18.7 (#254)
| Benchmark | Hy4 preview | Phi 3 Mini 128k Instruct |
|---|---|---|
| NYT Connections (extended) | 68.2% | — |
| LMArena Hard Prompts | — | 1028 |
Math Hy4 preview leads
Hy4 preview: 54.5 (#37), Phi 3 Mini 128k Instruct: 29.2 (#220)
| Benchmark | Hy4 preview | Phi 3 Mini 128k Instruct |
|---|---|---|
| ProofBench | 75% | — |
| LMArena Math | — | 1089 |
Knowledge Not comparable
Hy4 preview: —, Phi 3 Mini 128k Instruct: 26.3 (#251)
| Benchmark | Hy4 preview | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Expert | — | 984 |
Multilingual Not comparable
Hy4 preview: —, Phi 3 Mini 128k Instruct: 25.4 (#280)
| Benchmark | Hy4 preview | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Non-English | — | 1000 |
| LMArena Chinese | — | 1016 |
| LMArena French | — | 1038 |
| LMArena German | — | 1006 |
| LMArena Japanese | — | 899 |
| LMArena Korean | — | 856 |
| LMArena Russian | — | 1004 |
| LMArena Spanish | — | 1058 |
Instruction Following Not comparable
Hy4 preview: —, Phi 3 Mini 128k Instruct: 52.1 (#289)
| Benchmark | Hy4 preview | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Instruction Following | — | 1023 |
Long Context Not comparable
Hy4 preview: —, Phi 3 Mini 128k Instruct: 30.3 (#284)
| Benchmark | Hy4 preview | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Longer Query | — | 996 |
Writing & Preference Not comparable
Hy4 preview: —, Phi 3 Mini 128k Instruct: 27.3 (#296)
| Benchmark | Hy4 preview | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Text | — | 1050 |
| LMArena Creative Writing | — | 1024 |
| LMArena Multi-Turn | — | 989 |
Frequently asked questions
Is Hy4 preview better than Phi 3 Mini 128k Instruct?
Hy4 preview is the stronger model overall, scoring 44.6 to 29.1 on the Noometry Index.
Is Hy4 preview or Phi 3 Mini 128k Instruct better for coding?
Hy4 preview scores higher on coding benchmarks: 51.4 versus 28.3 in the Noometry coding category.
How many benchmarks do Hy4 preview and Phi 3 Mini 128k Instruct share?
0 benchmarks have published results for both models. Hy4 preview has 3 scored results on Noometry and Phi 3 Mini 128k Instruct has 19.