Model comparison
Hy3 vs MiMo-V2.6-Flash
MiMo-V2.6-Flash is the stronger model overall, scoring 48.5 to 44.2 on the Noometry Index.
Last verified . 15 shared benchmarks.
TencentSummary
- They share 15 benchmarks with published results for both. Hy3 scores higher in 0 categories and MiMo-V2.6-Flash in 8 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in math, where MiMo-V2.6-Flash leads 51.9 to 40.1.
- MiMo-V2.6-Flash is cheaper at $0.14 / $0.28 per million input/output tokens, against $0.13 / $0.53 for Hy3.
- MiMo-V2.6-Flash accepts more context: 1.05M tokens versus 262K.
Side by side
| Hy3 | MiMo-V2.6-Flash | |
|---|---|---|
| Provider | Tencent | Xiaomi |
| Noometry Index | 44.2 | 48.5 |
| Released | 2026-07-06 | 2026-09-21 |
| Weights | Open | Open |
| Context window | 262K | 1.05M |
| Max output | 128K | 131K |
| Input $ / M tokens | $0.13 | $0.14 |
| Output $ / M tokens | $0.53 | $0.28 |
| Results tracked | 19 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2.6-Flash leads
Hy3: 46.8 (#63), MiMo-V2.6-Flash: 53.4 (#30)
| Benchmark | Hy3 | MiMo-V2.6-Flash |
|---|---|---|
| LMArena WebDev | 1508 | 1637 |
| LMArena Coding | 1464 | 1504 |
| SciCode | — | 51.3% |
Reasoning MiMo-V2.6-Flash leads
Hy3: 26.1 (#136), MiMo-V2.6-Flash: 36.5 (#66)
| Benchmark | Hy3 | MiMo-V2.6-Flash |
|---|---|---|
| LMArena Hard Prompts | 1447 | 1482 |
| NYT Connections (extended) | 41.2% | — |
| CritPt | — | 12% |
Math MiMo-V2.6-Flash leads
Hy3: 40.1 (#93), MiMo-V2.6-Flash: 51.9 (#52)
| Benchmark | Hy3 | MiMo-V2.6-Flash |
|---|---|---|
| LMArena Math | 1475 | 1468 |
| ProofBench | — | 63% |
Knowledge MiMo-V2.6-Flash leads
Hy3: 40.8 (#114), MiMo-V2.6-Flash: 42.2 (#99)
| Benchmark | Hy3 | MiMo-V2.6-Flash |
|---|---|---|
| LMArena Expert | 1460 | 1501 |
Multimodal Not comparable
Hy3: —, MiMo-V2.6-Flash: 40.5 (#47)
| Benchmark | Hy3 | MiMo-V2.6-Flash |
|---|---|---|
| LMArena Vision | — | 1259 |
Multilingual Too close to call
Hy3: 53.5 (#65), MiMo-V2.6-Flash: 54.0 (#51)
| Benchmark | Hy3 | MiMo-V2.6-Flash |
|---|---|---|
| LMArena Non-English | 1426 | 1434 |
| LMArena Chinese | 1493 | 1511 |
| LMArena French | 1461 | 1475 |
| LMArena Russian | 1432 | 1409 |
| LMArena Spanish | 1456 | 1456 |
| LMArena German | 1439 | — |
| LMArena Japanese | 1392 | — |
| LMArena Korean | 1395 | — |
Instruction Following MiMo-V2.6-Flash leads
Hy3: 75.1 (#70), MiMo-V2.6-Flash: 76.8 (#35)
| Benchmark | Hy3 | MiMo-V2.6-Flash |
|---|---|---|
| LMArena Instruction Following | 1426 | 1463 |
Long Context Too close to call
Hy3: 44.1 (#75), MiMo-V2.6-Flash: 44.8 (#57)
| Benchmark | Hy3 | MiMo-V2.6-Flash |
|---|---|---|
| LMArena Longer Query | 1442 | 1463 |
Writing & Preference Too close to call
Hy3: 62.2 (#81), MiMo-V2.6-Flash: 63.1 (#67)
| Benchmark | Hy3 | MiMo-V2.6-Flash |
|---|---|---|
| LMArena Text | 1439 | 1455 |
| LMArena Creative Writing | 1402 | 1400 |
| LMArena Multi-Turn | 1436 | 1451 |
Frequently asked questions
Is Hy3 better than MiMo-V2.6-Flash?
MiMo-V2.6-Flash is the stronger model overall, scoring 48.5 to 44.2 on the Noometry Index.
Which is cheaper, Hy3 or MiMo-V2.6-Flash?
MiMo-V2.6-Flash is cheaper. It lists at $0.14 per million input tokens and $0.28 per million output tokens; Hy3 lists at $0.13 and $0.53.
Is Hy3 or MiMo-V2.6-Flash better for coding?
MiMo-V2.6-Flash scores higher on coding benchmarks: 53.4 versus 46.8 in the Noometry coding category.
Which has the bigger context window?
MiMo-V2.6-Flash does, with 1.05M tokens against 262K.
How many benchmarks do Hy3 and MiMo-V2.6-Flash share?
15 benchmarks have published results for both models. Hy3 has 19 scored results on Noometry and MiMo-V2.6-Flash has 19.