Model comparison
Hy3 vs MiMo-V2-Flash
Hy3 is the stronger model overall, scoring 44.2 to 41.3 on the Noometry Index.
Last verified . 18 shared benchmarks.
TencentSummary
- They share 18 benchmarks with published results for both. Hy3 scores higher in 8 categories and MiMo-V2-Flash in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where Hy3 leads 46.8 to 36.1.
- Hy3 is cheaper at $0.0825 / $0.33 per million input/output tokens, against $0.14 / $0.28 for MiMo-V2-Flash.
Side by side
| Hy3 | MiMo-V2-Flash | |
|---|---|---|
| Provider | Tencent | Xiaomi |
| Noometry Index | 44.2 | 41.3 |
| Released | 2026-07-06 | 2025-12-16 |
| Weights | Open | Open |
| Context window | 262K | 262K |
| Max output | 128K | 66K |
| Input $ / M tokens | $0.0825 | $0.14 |
| Output $ / M tokens | $0.33 | $0.28 |
| Results tracked | 19 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy3 leads
Hy3: 46.8 (#63), MiMo-V2-Flash: 36.1 (#211)
| Benchmark | Hy3 | MiMo-V2-Flash |
|---|---|---|
| LMArena WebDev | 1508 | 1330 |
| LMArena Coding | 1464 | 1443 |
| SciCode | — | 25.9% |
| ALE-Bench | — | 737.95 |
Reasoning Hy3 leads
Hy3: 26.1 (#136), MiMo-V2-Flash: 24.9 (#157)
| Benchmark | Hy3 | MiMo-V2-Flash |
|---|---|---|
| LMArena Hard Prompts | 1447 | 1420 |
| NYT Connections (extended) | 41.2% | — |
| CritPt | — | 0% |
Math Hy3 leads
Hy3: 40.1 (#93), MiMo-V2-Flash: 38.3 (#139)
| Benchmark | Hy3 | MiMo-V2-Flash |
|---|---|---|
| LMArena Math | 1475 | 1396 |
Knowledge Hy3 leads
Hy3: 40.8 (#114), MiMo-V2-Flash: 39.7 (#131)
| Benchmark | Hy3 | MiMo-V2-Flash |
|---|---|---|
| LMArena Expert | 1460 | 1425 |
Multilingual Hy3 leads
Hy3: 53.5 (#65), MiMo-V2-Flash: 51.0 (#113)
| Benchmark | Hy3 | MiMo-V2-Flash |
|---|---|---|
| LMArena Non-English | 1426 | 1392 |
| LMArena Chinese | 1493 | 1462 |
| LMArena French | 1461 | 1429 |
| LMArena German | 1439 | 1395 |
| LMArena Japanese | 1392 | 1325 |
| LMArena Korean | 1395 | 1358 |
| LMArena Russian | 1432 | 1387 |
| LMArena Spanish | 1456 | 1420 |
Instruction Following Hy3 leads
Hy3: 75.1 (#70), MiMo-V2-Flash: 73.5 (#120)
| Benchmark | Hy3 | MiMo-V2-Flash |
|---|---|---|
| LMArena Instruction Following | 1426 | 1392 |
Long Context Hy3 leads
Hy3: 44.1 (#75), MiMo-V2-Flash: 43.0 (#110)
| Benchmark | Hy3 | MiMo-V2-Flash |
|---|---|---|
| LMArena Longer Query | 1442 | 1409 |
Writing & Preference Hy3 leads
Hy3: 62.2 (#81), MiMo-V2-Flash: 59.7 (#106)
| Benchmark | Hy3 | MiMo-V2-Flash |
|---|---|---|
| LMArena Text | 1439 | 1411 |
| LMArena Creative Writing | 1402 | 1375 |
| LMArena Multi-Turn | 1436 | 1404 |
Frequently asked questions
Is Hy3 better than MiMo-V2-Flash?
Hy3 is the stronger model overall, scoring 44.2 to 41.3 on the Noometry Index.
Which is cheaper, Hy3 or MiMo-V2-Flash?
Hy3 is cheaper. It lists at $0.0825 per million input tokens and $0.33 per million output tokens; MiMo-V2-Flash lists at $0.14 and $0.28.
Is Hy3 or MiMo-V2-Flash better for coding?
Hy3 scores higher on coding benchmarks: 46.8 versus 36.1 in the Noometry coding category.
Which has the bigger context window?
Both accept 262K tokens.
How many benchmarks do Hy3 and MiMo-V2-Flash share?
18 benchmarks have published results for both models. Hy3 has 19 scored results on Noometry and MiMo-V2-Flash has 21.