Model comparison
Hy4 preview vs MiMo-V2.5
Hy4 preview is the stronger model overall, scoring 45.3 to 43.4 on the Noometry Index. MiMo-V2.5 costs 6.4× less per token, which makes it the better buy when Hy4 preview's lead doesn't matter for your workload.
Last verified . 2 shared benchmarks.
TencentSummary
- They share 2 benchmarks with published results for both. Hy4 preview scores higher in 3 categories and MiMo-V2.5 in 0 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in math, where Hy4 preview leads 55.7 to 36.8.
- The biggest single-benchmark swing is ProofBench: 75% for Hy4 preview and 16% for MiMo-V2.5.
- MiMo-V2.5 is cheaper at $0.14 / $0.28 per million input/output tokens, against $0.75 / $2.25 for Hy4 preview.
Side by side
| Hy4 preview | MiMo-V2.5 | |
|---|---|---|
| Provider | Tencent | Xiaomi |
| Noometry Index | 45.3 | 43.4 |
| Released | 2026-08-28 | 2026-04-22 |
| Weights | Open | Open |
| Context window | 1.05M | 1.05M |
| Max output | 64K | 131K |
| Input $ / M tokens | $0.75 | $0.14 |
| Output $ / M tokens | $2.25 | $0.28 |
| Results tracked | 3 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy4 preview leads
Hy4 preview: 51.6 (#38), MiMo-V2.5: 43.9 (#81)
| Benchmark | Hy4 preview | MiMo-V2.5 |
|---|---|---|
| LMArena WebDev | 1632 | 1438 |
| SciCode | — | 43.1% |
| LMArena Coding | — | 1469 |
| ALE-Bench | — | 513.95 |
Reasoning Hy4 preview leads
Hy4 preview: 31.9 (#79), MiMo-V2.5: 28.6 (#101)
| Benchmark | Hy4 preview | MiMo-V2.5 |
|---|---|---|
| NYT Connections (extended) | 68.2% | — |
| CritPt | — | 3.7% |
| LMArena Hard Prompts | — | 1450 |
Math Hy4 preview leads
Hy4 preview: 55.7 (#42), MiMo-V2.5: 36.8 (#163)
| Benchmark | Hy4 preview | MiMo-V2.5 |
|---|---|---|
| ProofBench | 75% | 16% |
| LMArena Math | — | 1436 |
Knowledge Not comparable
Hy4 preview: —, MiMo-V2.5: 40.8 (#115)
| Benchmark | Hy4 preview | MiMo-V2.5 |
|---|---|---|
| LMArena Expert | — | 1460 |
Multimodal Not comparable
Hy4 preview: —, MiMo-V2.5: 39.8 (#54)
| Benchmark | Hy4 preview | MiMo-V2.5 |
|---|---|---|
| LMArena Vision | — | 1247 |
Multilingual Not comparable
Hy4 preview: —, MiMo-V2.5: 51.9 (#99)
| Benchmark | Hy4 preview | MiMo-V2.5 |
|---|---|---|
| LMArena Non-English | — | 1404 |
| LMArena Chinese | — | 1468 |
| LMArena French | — | 1447 |
| LMArena German | — | 1421 |
| LMArena Japanese | — | 1306 |
| LMArena Korean | — | 1363 |
| LMArena Russian | — | 1395 |
| LMArena Spanish | — | 1416 |
Instruction Following Not comparable
Hy4 preview: —, MiMo-V2.5: 75.5 (#60)
| Benchmark | Hy4 preview | MiMo-V2.5 |
|---|---|---|
| LMArena Instruction Following | — | 1434 |
Long Context Not comparable
Hy4 preview: —, MiMo-V2.5: 44.2 (#73)
| Benchmark | Hy4 preview | MiMo-V2.5 |
|---|---|---|
| LMArena Longer Query | — | 1445 |
Writing & Preference Not comparable
Hy4 preview: —, MiMo-V2.5: 61.6 (#86)
| Benchmark | Hy4 preview | MiMo-V2.5 |
|---|---|---|
| LMArena Text | — | 1428 |
| LMArena Creative Writing | — | 1393 |
| LMArena Multi-Turn | — | 1445 |
Frequently asked questions
Is Hy4 preview better than MiMo-V2.5?
Hy4 preview is the stronger model overall, scoring 45.3 to 43.4 on the Noometry Index. MiMo-V2.5 costs 6.4× less per token, which makes it the better buy when Hy4 preview's lead doesn't matter for your workload.
Which is cheaper, Hy4 preview or MiMo-V2.5?
MiMo-V2.5 is cheaper. It lists at $0.14 per million input tokens and $0.28 per million output tokens; Hy4 preview lists at $0.75 and $2.25.
Is Hy4 preview or MiMo-V2.5 better for coding?
Hy4 preview scores higher on coding benchmarks: 51.6 versus 43.9 in the Noometry coding category.
Which has the bigger context window?
Both accept 1.05M tokens.
How many benchmarks do Hy4 preview and MiMo-V2.5 share?
2 benchmarks have published results for both models. Hy4 preview has 3 scored results on Noometry and MiMo-V2.5 has 23.