Model comparison
Gemma 3 27B vs MiMo-V2-Flash
MiMo-V2-Flash is the stronger model overall, scoring 41.3 to 30.8 on the Noometry Index. Gemma 3 27B costs 1.8× less per token, which makes it the better buy when MiMo-V2-Flash's lead doesn't matter for your workload.
Last verified . 19 shared benchmarks.
GoogleSummary
- They share 19 benchmarks with published results for both. Gemma 3 27B scores higher in 0 categories and MiMo-V2-Flash in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in long context, where MiMo-V2-Flash leads 43.0 to 27.6.
- Gemma 3 27B is cheaper at $0.08 / $0.16 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 27B | MiMo-V2-Flash | |
|---|---|---|
| Provider | Xiaomi | |
| Noometry Index | 30.8 | 41.3 |
| Released | 2025-03-11 | 2025-12-16 |
| Weights | Open | Open |
| Context window | 131K | 262K |
| Max output | 8K | 66K |
| Input $ / M tokens | $0.08 | $0.14 |
| Output $ / M tokens | $0.16 | $0.28 |
| Results tracked | 43 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2-Flash leads
Gemma 3 27B: 22.5 (#334), MiMo-V2-Flash: 36.1 (#211)
| Benchmark | Gemma 3 27B | MiMo-V2-Flash |
|---|---|---|
| SciCode | 21.2% | 25.9% |
| LMArena Coding | 1322 | 1443 |
| Aider Polyglot | 4.9% | — |
| LMArena WebDev | — | 1330 |
| LiveBench Coding | 39.9% | — |
| ALE-Bench | — | 737.95 |
Agentic & Tool Use Not comparable
Gemma 3 27B: 25.1 (#110), MiMo-V2-Flash: —
| Benchmark | Gemma 3 27B | MiMo-V2-Flash |
|---|---|---|
| Berkeley Function Calling Leaderboard | 29.5% | — |
Reasoning MiMo-V2-Flash leads
Gemma 3 27B: 16.7 (#301), MiMo-V2-Flash: 24.9 (#157)
| Benchmark | Gemma 3 27B | MiMo-V2-Flash |
|---|---|---|
| CritPt | 0% | 0% |
| LMArena Hard Prompts | 1340 | 1420 |
| Kagi LLM Benchmark | 40.4% | — |
| Chess Puzzles | 0% | — |
| LiveBench Reasoning | 43.8% | — |
| DTBench | 52.5% | — |
| LiveBench Data Analysis | 51.5% | — |
| LMCA | 12.3% | — |
| Epoch Capabilities Index | 130.04 | — |
| LiveBench | 50% | — |
Math MiMo-V2-Flash leads
Gemma 3 27B: 25.9 (#265), MiMo-V2-Flash: 38.3 (#139)
| Benchmark | Gemma 3 27B | MiMo-V2-Flash |
|---|---|---|
| LMArena Math | 1312 | 1396 |
| OTIS Mock AIME 2024-2025 | 22.5% | — |
| LiveBench Math | 55.4% | — |
| MATH Level 5 | 74% | — |
Knowledge MiMo-V2-Flash leads
Gemma 3 27B: 25.5 (#261), MiMo-V2-Flash: 39.7 (#131)
| Benchmark | Gemma 3 27B | MiMo-V2-Flash |
|---|---|---|
| LMArena Expert | 1304 | 1425 |
| GPQA Diamond | 47.7% | — |
| Confabulations | 40.3% | — |
| Vectara Hallucination Rate | 7.4% | — |
Multimodal Not comparable
Gemma 3 27B: 32.6 (#100), MiMo-V2-Flash: —
| Benchmark | Gemma 3 27B | MiMo-V2-Flash |
|---|---|---|
| LMArena Vision | 1164 | — |
| GeoBench | 52% | — |
Multilingual MiMo-V2-Flash leads
Gemma 3 27B: 46.9 (#155), MiMo-V2-Flash: 51.0 (#113)
| Benchmark | Gemma 3 27B | MiMo-V2-Flash |
|---|---|---|
| LMArena Non-English | 1334 | 1392 |
| LMArena Chinese | 1346 | 1462 |
| LMArena French | 1368 | 1429 |
| LMArena German | 1362 | 1395 |
| LMArena Japanese | 1287 | 1325 |
| LMArena Korean | 1308 | 1358 |
| LMArena Russian | 1349 | 1387 |
| LMArena Spanish | 1349 | 1420 |
Instruction Following MiMo-V2-Flash leads
Gemma 3 27B: 70.6 (#160), MiMo-V2-Flash: 73.5 (#120)
| Benchmark | Gemma 3 27B | MiMo-V2-Flash |
|---|---|---|
| LMArena Instruction Following | 1321 | 1392 |
| LiveBench Instruction Following | 74.9% | — |
Long Context MiMo-V2-Flash leads
Gemma 3 27B: 27.6 (#293), MiMo-V2-Flash: 43.0 (#110)
| Benchmark | Gemma 3 27B | MiMo-V2-Flash |
|---|---|---|
| LMArena Longer Query | 1333 | 1409 |
| Fiction.LiveBench | 33.3% | — |
Writing & Preference MiMo-V2-Flash leads
Gemma 3 27B: 52.5 (#168), MiMo-V2-Flash: 59.7 (#106)
| Benchmark | Gemma 3 27B | MiMo-V2-Flash |
|---|---|---|
| LMArena Text | 1358 | 1411 |
| LMArena Creative Writing | 1346 | 1375 |
| LMArena Multi-Turn | 1345 | 1404 |
| Short-Story Creative Writing | 79.9% | — |
| EQ-Bench Creative Writing | 1266 | — |
| LiveBench Language | 34.6% | — |
Frequently asked questions
Is Gemma 3 27B better than MiMo-V2-Flash?
MiMo-V2-Flash is the stronger model overall, scoring 41.3 to 30.8 on the Noometry Index. Gemma 3 27B costs 1.8× 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 27B or MiMo-V2-Flash?
Gemma 3 27B is cheaper. It lists at $0.08 per million input tokens and $0.16 per million output tokens; MiMo-V2-Flash lists at $0.14 and $0.28.
Is Gemma 3 27B or MiMo-V2-Flash better for coding?
MiMo-V2-Flash scores higher on coding benchmarks: 36.1 versus 22.5 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 27B and MiMo-V2-Flash share?
19 benchmarks have published results for both models. Gemma 3 27B has 43 scored results on Noometry and MiMo-V2-Flash has 21.