Model comparison
Hy3 vs MiMo-V2.5-Pro
MiMo-V2.5-Pro is the stronger model overall, scoring 45.2 to 44.2 on the Noometry Index. Hy3 costs 3.8× less per token, which makes it the better buy when MiMo-V2.5-Pro's lead doesn't matter for your workload.
Last verified . 19 shared benchmarks.
TencentSummary
- They share 19 benchmarks with published results for both. Hy3 scores higher in 1 category and MiMo-V2.5-Pro in 7 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiMo-V2.5-Pro leads 65.3 to 62.2.
- The biggest single-benchmark swing is NYT Connections (extended): 41.2% for Hy3 and 34.4% for MiMo-V2.5-Pro.
- Hy3 is cheaper at $0.0825 / $0.33 per million input/output tokens, against $0.43 / $0.87 for MiMo-V2.5-Pro.
- MiMo-V2.5-Pro accepts more context: 1.05M tokens versus 262K.
Side by side
| Hy3 | MiMo-V2.5-Pro | |
|---|---|---|
| Provider | Tencent | Xiaomi |
| Noometry Index | 44.2 | 45.2 |
| Released | 2026-07-06 | 2026-04-22 |
| Weights | Open | Open |
| Context window | 262K | 1.05M |
| Max output | 128K | 131K |
| Input $ / M tokens | $0.0825 | $0.43 |
| Output $ / M tokens | $0.33 | $0.87 |
| Results tracked | 19 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Hy3: 46.8 (#63), MiMo-V2.5-Pro: 47.4 (#60)
| Benchmark | Hy3 | MiMo-V2.5-Pro |
|---|---|---|
| LMArena WebDev | 1508 | 1479 |
| LMArena Coding | 1464 | 1503 |
| SciCode | — | 50.2% |
| ALE-Bench | — | 899.8 |
Reasoning Too close to call
Hy3: 26.1 (#136), MiMo-V2.5-Pro: 26.8 (#130)
| Benchmark | Hy3 | MiMo-V2.5-Pro |
|---|---|---|
| NYT Connections (extended) | 41.2% | 34.4% |
| LMArena Hard Prompts | 1447 | 1488 |
| CritPt | — | 4% |
| DTBench | — | 84.5% |
| LMCA | — | 29.5% |
Math Too close to call
Hy3: 40.1 (#93), MiMo-V2.5-Pro: 40.0 (#96)
| Benchmark | Hy3 | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Math | 1475 | 1481 |
| ProofBench | — | 22% |
Knowledge MiMo-V2.5-Pro leads
Hy3: 40.8 (#114), MiMo-V2.5-Pro: 42.2 (#98)
| Benchmark | Hy3 | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Expert | 1460 | 1503 |
Multilingual MiMo-V2.5-Pro leads
Hy3: 53.5 (#65), MiMo-V2.5-Pro: 55.1 (#34)
| Benchmark | Hy3 | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Non-English | 1426 | 1449 |
| LMArena Chinese | 1493 | 1507 |
| LMArena French | 1461 | 1488 |
| LMArena German | 1439 | 1458 |
| LMArena Japanese | 1392 | 1412 |
| LMArena Korean | 1395 | 1437 |
| LMArena Russian | 1432 | 1450 |
| LMArena Spanish | 1456 | 1471 |
Instruction Following MiMo-V2.5-Pro leads
Hy3: 75.1 (#70), MiMo-V2.5-Pro: 77.5 (#21)
| Benchmark | Hy3 | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Instruction Following | 1426 | 1477 |
Long Context MiMo-V2.5-Pro leads
Hy3: 44.1 (#75), MiMo-V2.5-Pro: 45.4 (#37)
| Benchmark | Hy3 | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Longer Query | 1442 | 1483 |
Writing & Preference MiMo-V2.5-Pro leads
Hy3: 62.2 (#81), MiMo-V2.5-Pro: 65.3 (#49)
| Benchmark | Hy3 | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Text | 1439 | 1465 |
| LMArena Creative Writing | 1402 | 1440 |
| LMArena Multi-Turn | 1436 | 1477 |
| EQ-Bench Creative Writing | — | 1493 |
| EQ-Bench 4 | — | 1208 |
Frequently asked questions
Is Hy3 better than MiMo-V2.5-Pro?
MiMo-V2.5-Pro is the stronger model overall, scoring 45.2 to 44.2 on the Noometry Index. Hy3 costs 3.8× less per token, which makes it the better buy when MiMo-V2.5-Pro's lead doesn't matter for your workload.
Which is cheaper, Hy3 or MiMo-V2.5-Pro?
Hy3 is cheaper. It lists at $0.0825 per million input tokens and $0.33 per million output tokens; MiMo-V2.5-Pro lists at $0.43 and $0.87.
Is Hy3 or MiMo-V2.5-Pro better for coding?
They score almost the same on coding (46.8 vs 47.4); test both on your own repository before choosing.
Which has the bigger context window?
MiMo-V2.5-Pro does, with 1.05M tokens against 262K.
How many benchmarks do Hy3 and MiMo-V2.5-Pro share?
19 benchmarks have published results for both models. Hy3 has 19 scored results on Noometry and MiMo-V2.5-Pro has 27.