Model comparison
Hy3 vs MiMo-V2-Pro
Hy3 is the stronger model overall, scoring 44.2 to 43.0 on the Noometry Index.
Last verified . 19 shared benchmarks.
TencentSummary
- They share 19 benchmarks with published results for both. Hy3 scores higher in 5 categories and MiMo-V2-Pro in 3 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Hy3 leads 26.1 to 22.1.
- The biggest single-benchmark swing is NYT Connections (extended): 41.2% for Hy3 and 25.8% for MiMo-V2-Pro.
- Hy3 is cheaper at $0.13 / $0.53 per million input/output tokens, against $0.43 / $0.87 for MiMo-V2-Pro.
- MiMo-V2-Pro accepts more context: 1.05M tokens versus 262K.
- Hy3 has downloadable open weights; the other is API-only.
Side by side
| Hy3 | MiMo-V2-Pro | |
|---|---|---|
| Provider | Tencent | Xiaomi |
| Noometry Index | 44.2 | 43.0 |
| Released | 2026-07-06 | 2026-03-18 |
| Weights | Open | Proprietary |
| Context window | 262K | 1.05M |
| Max output | 128K | 131K |
| Input $ / M tokens | $0.13 | $0.43 |
| Output $ / M tokens | $0.53 | $0.87 |
| Results tracked | 19 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy3 leads
Hy3: 46.8 (#63), MiMo-V2-Pro: 43.8 (#83)
| Benchmark | Hy3 | MiMo-V2-Pro |
|---|---|---|
| LMArena WebDev | 1508 | 1433 |
| LMArena Coding | 1464 | 1476 |
| ALE-Bench | — | 785.17 |
Reasoning Hy3 leads
Hy3: 26.1 (#136), MiMo-V2-Pro: 22.1 (#206)
| Benchmark | Hy3 | MiMo-V2-Pro |
|---|---|---|
| NYT Connections (extended) | 41.2% | 25.8% |
| LMArena Hard Prompts | 1447 | 1457 |
| Thematic Generalization | — | 45.9% |
Math Too close to call
Hy3: 40.1 (#93), MiMo-V2-Pro: 39.5 (#102)
| Benchmark | Hy3 | MiMo-V2-Pro |
|---|---|---|
| LMArena Math | 1475 | 1447 |
Knowledge Too close to call
Hy3: 40.8 (#114), MiMo-V2-Pro: 41.4 (#111)
| Benchmark | Hy3 | MiMo-V2-Pro |
|---|---|---|
| LMArena Expert | 1460 | 1478 |
Multilingual Too close to call
Hy3: 53.5 (#65), MiMo-V2-Pro: 52.7 (#81)
| Benchmark | Hy3 | MiMo-V2-Pro |
|---|---|---|
| LMArena Non-English | 1426 | 1416 |
| LMArena Chinese | 1493 | 1456 |
| LMArena French | 1461 | 1469 |
| LMArena German | 1439 | 1417 |
| LMArena Japanese | 1392 | 1366 |
| LMArena Korean | 1395 | 1400 |
| LMArena Russian | 1432 | 1427 |
| LMArena Spanish | 1456 | 1457 |
Instruction Following Too close to call
Hy3: 75.1 (#70), MiMo-V2-Pro: 76.0 (#49)
| Benchmark | Hy3 | MiMo-V2-Pro |
|---|---|---|
| LMArena Instruction Following | 1426 | 1445 |
Long Context Hy3 leads
Hy3: 44.1 (#75), MiMo-V2-Pro: 41.5 (#138)
| Benchmark | Hy3 | MiMo-V2-Pro |
|---|---|---|
| LMArena Longer Query | 1442 | 1455 |
| CL-bench | — | 15.7% |
| CL-bench Life | — | 6.9% |
Writing & Preference Too close to call
Hy3: 62.2 (#81), MiMo-V2-Pro: 62.8 (#70)
| Benchmark | Hy3 | MiMo-V2-Pro |
|---|---|---|
| LMArena Text | 1439 | 1436 |
| LMArena Creative Writing | 1402 | 1415 |
| LMArena Multi-Turn | 1436 | 1456 |
Frequently asked questions
Is Hy3 better than MiMo-V2-Pro?
Hy3 is the stronger model overall, scoring 44.2 to 43.0 on the Noometry Index.
Which is cheaper, Hy3 or MiMo-V2-Pro?
Hy3 is cheaper. It lists at $0.13 per million input tokens and $0.53 per million output tokens; MiMo-V2-Pro lists at $0.43 and $0.87.
Is Hy3 or MiMo-V2-Pro better for coding?
Hy3 scores higher on coding benchmarks: 46.8 versus 43.8 in the Noometry coding category.
Which has the bigger context window?
MiMo-V2-Pro does, with 1.05M tokens against 262K.
How many benchmarks do Hy3 and MiMo-V2-Pro share?
19 benchmarks have published results for both models. Hy3 has 19 scored results on Noometry and MiMo-V2-Pro has 23.