Model comparison
Hy3 vs MiMo-V2-Pro
Hy3 is the stronger model overall, scoring 43.6 to 42.4 on the Noometry Index.
Last verified . 17 shared benchmarks.
TencentSummary
- They share 17 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 25.0 to 21.3.
- 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 | 43.6 | 42.4 |
| 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 | 17 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy3 leads
Hy3: 46.6 (#60), MiMo-V2-Pro: 43.4 (#76)
| Benchmark | Hy3 | MiMo-V2-Pro |
|---|---|---|
| LMArena WebDev | 1509 | 1433 |
| LMArena Coding | 1465 | 1476 |
| ALE-Bench | — | 785.17 |
Reasoning Hy3 leads
Hy3: 25.0 (#134), MiMo-V2-Pro: 21.3 (#200)
| Benchmark | Hy3 | MiMo-V2-Pro |
|---|---|---|
| NYT Connections (extended) | 41.2% | 25.8% |
| LMArena Hard Prompts | 1449 | 1457 |
| Thematic Generalization | — | 45.9% |
Math Too close to call
Hy3: 37.4 (#98), MiMo-V2-Pro: 36.7 (#104)
| Benchmark | Hy3 | MiMo-V2-Pro |
|---|---|---|
| LMArena Math | 1475 | 1447 |
Knowledge Too close to call
Hy3: 40.2 (#108), MiMo-V2-Pro: 40.8 (#106)
| Benchmark | Hy3 | MiMo-V2-Pro |
|---|---|---|
| LMArena Expert | 1461 | 1479 |
Multilingual Too close to call
Hy3: 53.7 (#60), MiMo-V2-Pro: 52.9 (#77)
| Benchmark | Hy3 | MiMo-V2-Pro |
|---|---|---|
| LMArena Non-English | 1427 | 1416 |
| LMArena Chinese | 1496 | 1455 |
| LMArena French | 1461 | 1470 |
| LMArena Korean | 1390 | 1401 |
| LMArena Russian | 1435 | 1427 |
| LMArena Spanish | 1448 | 1458 |
| LMArena German | — | 1417 |
| LMArena Japanese | — | 1366 |
Instruction Following Too close to call
Hy3: 75.3 (#68), MiMo-V2-Pro: 76.2 (#46)
| Benchmark | Hy3 | MiMo-V2-Pro |
|---|---|---|
| LMArena Instruction Following | 1425 | 1444 |
Long Context Hy3 leads
Hy3: 44.1 (#70), MiMo-V2-Pro: 41.5 (#133)
| Benchmark | Hy3 | MiMo-V2-Pro |
|---|---|---|
| LMArena Longer Query | 1443 | 1455 |
| CL-bench | — | 15.7% |
| CL-bench Life | — | 6.9% |
Writing & Preference Too close to call
Hy3: 62.5 (#75), MiMo-V2-Pro: 62.9 (#67)
| Benchmark | Hy3 | MiMo-V2-Pro |
|---|---|---|
| LMArena Text | 1442 | 1436 |
| LMArena Creative Writing | 1399 | 1415 |
| LMArena Multi-Turn | 1436 | 1456 |
Frequently asked questions
Is Hy3 better than MiMo-V2-Pro?
Hy3 is the stronger model overall, scoring 43.6 to 42.4 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: 46.6 versus 43.4 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?
17 benchmarks have published results for both models. Hy3 has 17 scored results on Noometry and MiMo-V2-Pro has 23.