Model comparison
Gemma 3 12B vs MiMo-V2-Flash
MiMo-V2-Flash is the stronger model overall, scoring 40.8 to 31.8 on the Noometry Index. Gemma 3 12B costs 2.3× less per token, which makes it the better buy when MiMo-V2-Flash's lead doesn't matter for your workload.
Last verified . 14 shared benchmarks.
GoogleSummary
- They share 14 benchmarks with published results for both. Gemma 3 12B scores higher in 0 categories and MiMo-V2-Flash in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where MiMo-V2-Flash leads 35.6 to 21.0.
- The biggest single-benchmark swing is SciCode: 17.4% for Gemma 3 12B and 25.9% for MiMo-V2-Flash.
- Gemma 3 12B is cheaper at $0.05 / $0.15 per million input/output tokens, against $0.14 / $0.28 for MiMo-V2-Flash.
- MiMo-V2-Flash accepts more context: 262K tokens versus 131K.
Side by side
| Gemma 3 12B | MiMo-V2-Flash | |
|---|---|---|
| Provider | Xiaomi | |
| Noometry Index | 31.8 | 40.8 |
| Released | 2025-03-12 | 2025-12-16 |
| Weights | Open | Open |
| Context window | 131K | 262K |
| Max output | 8K | 66K |
| Input $ / M tokens | $0.05 | $0.14 |
| Output $ / M tokens | $0.15 | $0.28 |
| Results tracked | 24 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2-Flash leads
Gemma 3 12B: 31.2 (#276), MiMo-V2-Flash: 35.8 (#205)
| Benchmark | Gemma 3 12B | MiMo-V2-Flash |
|---|---|---|
| SciCode | 17.4% | 25.9% |
| LMArena Coding | 1281 | 1443 |
| LMArena WebDev | — | 1330 |
| ALE-Bench | — | 737.95 |
Agentic & Tool Use Not comparable
Gemma 3 12B: 25.3 (#101), MiMo-V2-Flash: —
| Benchmark | Gemma 3 12B | MiMo-V2-Flash |
|---|---|---|
| Berkeley Function Calling Leaderboard | 30.4% | — |
Reasoning MiMo-V2-Flash leads
Gemma 3 12B: 15.2 (#307), MiMo-V2-Flash: 24.1 (#155)
| Benchmark | Gemma 3 12B | MiMo-V2-Flash |
|---|---|---|
| CritPt | 0% | 0% |
| LMArena Hard Prompts | 1309 | 1420 |
| Chess Puzzles | 0% | — |
| DTBench | 48.8% | — |
| LMCA | 4.5% | — |
| Epoch Capabilities Index | 123.49 | — |
Math MiMo-V2-Flash leads
Gemma 3 12B: 21.0 (#273), MiMo-V2-Flash: 35.6 (#141)
| Benchmark | Gemma 3 12B | MiMo-V2-Flash |
|---|---|---|
| LMArena Math | 1307 | 1396 |
| OTIS Mock AIME 2024-2025 | 16.7% | — |
Knowledge MiMo-V2-Flash leads
Gemma 3 12B: 26.5 (#250), MiMo-V2-Flash: 39.1 (#126)
| Benchmark | Gemma 3 12B | MiMo-V2-Flash |
|---|---|---|
| LMArena Expert | 1248 | 1425 |
| GPQA Diamond | 39.5% | — |
| Vectara Hallucination Rate | 4.4% | — |
Multimodal Not comparable
Gemma 3 12B: —, MiMo-V2-Flash: —
| Benchmark | Gemma 3 12B | MiMo-V2-Flash |
|---|---|---|
| MindCube | 46.7% | — |
Multilingual MiMo-V2-Flash leads
Gemma 3 12B: 45.9 (#160), MiMo-V2-Flash: 51.1 (#109)
| Benchmark | Gemma 3 12B | MiMo-V2-Flash |
|---|---|---|
| LMArena Non-English | 1318 | 1391 |
| LMArena German | 1370 | 1395 |
| LMArena Russian | 1335 | 1387 |
| LMArena Chinese | — | 1463 |
| LMArena French | — | 1429 |
| LMArena Japanese | — | 1324 |
| LMArena Korean | — | 1358 |
| LMArena Spanish | — | 1420 |
Instruction Following MiMo-V2-Flash leads
Gemma 3 12B: 68.8 (#179), MiMo-V2-Flash: 73.7 (#115)
| Benchmark | Gemma 3 12B | MiMo-V2-Flash |
|---|---|---|
| LMArena Instruction Following | 1299 | 1392 |
Long Context MiMo-V2-Flash leads
Gemma 3 12B: 40.0 (#157), MiMo-V2-Flash: 43.0 (#106)
| Benchmark | Gemma 3 12B | MiMo-V2-Flash |
|---|---|---|
| LMArena Longer Query | 1317 | 1409 |
Writing & Preference MiMo-V2-Flash leads
Gemma 3 12B: 47.7 (#205), MiMo-V2-Flash: 59.9 (#101)
| Benchmark | Gemma 3 12B | MiMo-V2-Flash |
|---|---|---|
| LMArena Text | 1334 | 1411 |
| LMArena Creative Writing | 1331 | 1375 |
| LMArena Multi-Turn | 1334 | 1404 |
| EQ-Bench Creative Writing | 1126 | — |
Frequently asked questions
Is Gemma 3 12B better than MiMo-V2-Flash?
MiMo-V2-Flash is the stronger model overall, scoring 40.8 to 31.8 on the Noometry Index. Gemma 3 12B costs 2.3× less per token, which makes it the better buy when MiMo-V2-Flash's lead doesn't matter for your workload.
Which is cheaper, Gemma 3 12B or MiMo-V2-Flash?
Gemma 3 12B is cheaper. It lists at $0.05 per million input tokens and $0.15 per million output tokens; MiMo-V2-Flash lists at $0.14 and $0.28.
Is Gemma 3 12B or MiMo-V2-Flash better for coding?
MiMo-V2-Flash scores higher on coding benchmarks: 35.8 versus 31.2 in the Noometry coding category.
Which has the bigger context window?
MiMo-V2-Flash does, with 262K tokens against 131K.
How many benchmarks do Gemma 3 12B and MiMo-V2-Flash share?
14 benchmarks have published results for both models. Gemma 3 12B has 24 scored results on Noometry and MiMo-V2-Flash has 21.