Model comparison
Gemma 3 27B vs MiMo-V2-Pro
MiMo-V2-Pro is the stronger model overall, scoring 42.4 to 30.5 on the Noometry Index. Gemma 3 27B costs 5.4× less per token, which makes it the better buy when MiMo-V2-Pro's lead doesn't matter for your workload.
Last verified . 17 shared benchmarks.
GoogleSummary
- They share 17 benchmarks with published results for both. Gemma 3 27B scores higher in 0 categories and MiMo-V2-Pro in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where MiMo-V2-Pro leads 43.4 to 22.1.
- Gemma 3 27B is cheaper at $0.08 / $0.16 per million input/output tokens, against $0.43 / $0.87 for MiMo-V2-Pro.
- MiMo-V2-Pro accepts more context: 1.05M tokens versus 131K.
- Gemma 3 27B has downloadable open weights; the other is API-only.
Side by side
| Gemma 3 27B | MiMo-V2-Pro | |
|---|---|---|
| Provider | Xiaomi | |
| Noometry Index | 30.5 | 42.4 |
| Released | 2025-03-11 | 2026-03-18 |
| Weights | Open | Proprietary |
| Context window | 131K | 1.05M |
| Max output | 8K | 131K |
| Input $ / M tokens | $0.08 | $0.43 |
| Output $ / M tokens | $0.16 | $0.87 |
| Results tracked | 43 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2-Pro leads
Gemma 3 27B: 22.1 (#329), MiMo-V2-Pro: 43.4 (#76)
| Benchmark | Gemma 3 27B | MiMo-V2-Pro |
|---|---|---|
| LMArena Coding | 1322 | 1476 |
| Aider Polyglot | 4.9% | — |
| LMArena WebDev | — | 1433 |
| SciCode | 21.2% | — |
| LiveBench Coding | 39.9% | — |
| ALE-Bench | — | 785.17 |
Agentic & Tool Use Not comparable
Gemma 3 27B: 24.9 (#105), MiMo-V2-Pro: —
| Benchmark | Gemma 3 27B | MiMo-V2-Pro |
|---|---|---|
| Berkeley Function Calling Leaderboard | 29.5% | — |
Reasoning MiMo-V2-Pro leads
Gemma 3 27B: 16.3 (#297), MiMo-V2-Pro: 21.3 (#200)
| Benchmark | Gemma 3 27B | MiMo-V2-Pro |
|---|---|---|
| LMArena Hard Prompts | 1340 | 1457 |
| Kagi LLM Benchmark | 40.4% | — |
| NYT Connections (extended) | — | 25.8% |
| CritPt | 0% | — |
| Chess Puzzles | 0% | — |
| Thematic Generalization | — | 45.9% |
| 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-Pro leads
Gemma 3 27B: 24.4 (#261), MiMo-V2-Pro: 36.7 (#104)
| Benchmark | Gemma 3 27B | MiMo-V2-Pro |
|---|---|---|
| LMArena Math | 1312 | 1447 |
| OTIS Mock AIME 2024-2025 | 22.5% | — |
| LiveBench Math | 55.4% | — |
| MATH Level 5 | 74% | — |
Knowledge MiMo-V2-Pro leads
Gemma 3 27B: 25.4 (#256), MiMo-V2-Pro: 40.8 (#106)
| Benchmark | Gemma 3 27B | MiMo-V2-Pro |
|---|---|---|
| LMArena Expert | 1303 | 1479 |
| GPQA Diamond | 47.7% | — |
| Confabulations | 40.3% | — |
| Vectara Hallucination Rate | 7.4% | — |
Multimodal Not comparable
Gemma 3 27B: 32.0 (#94), MiMo-V2-Pro: —
| Benchmark | Gemma 3 27B | MiMo-V2-Pro |
|---|---|---|
| LMArena Vision | 1165 | — |
| GeoBench | 52% | — |
Multilingual MiMo-V2-Pro leads
Gemma 3 27B: 47.0 (#150), MiMo-V2-Pro: 52.9 (#77)
| Benchmark | Gemma 3 27B | MiMo-V2-Pro |
|---|---|---|
| LMArena Non-English | 1334 | 1416 |
| LMArena Chinese | 1347 | 1455 |
| LMArena French | 1368 | 1470 |
| LMArena German | 1362 | 1417 |
| LMArena Japanese | 1287 | 1366 |
| LMArena Korean | 1308 | 1401 |
| LMArena Russian | 1349 | 1427 |
| LMArena Spanish | 1348 | 1458 |
Instruction Following MiMo-V2-Pro leads
Gemma 3 27B: 70.8 (#155), MiMo-V2-Pro: 76.2 (#46)
| Benchmark | Gemma 3 27B | MiMo-V2-Pro |
|---|---|---|
| LMArena Instruction Following | 1321 | 1444 |
| LiveBench Instruction Following | 74.9% | — |
Long Context MiMo-V2-Pro leads
Gemma 3 27B: 27.6 (#288), MiMo-V2-Pro: 41.5 (#133)
| Benchmark | Gemma 3 27B | MiMo-V2-Pro |
|---|---|---|
| LMArena Longer Query | 1333 | 1455 |
| Fiction.LiveBench | 33.3% | — |
| CL-bench | — | 15.7% |
| CL-bench Life | — | 6.9% |
Writing & Preference MiMo-V2-Pro leads
Gemma 3 27B: 52.7 (#161), MiMo-V2-Pro: 62.9 (#67)
| Benchmark | Gemma 3 27B | MiMo-V2-Pro |
|---|---|---|
| LMArena Text | 1358 | 1436 |
| LMArena Creative Writing | 1346 | 1415 |
| LMArena Multi-Turn | 1344 | 1456 |
| 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-Pro?
MiMo-V2-Pro is the stronger model overall, scoring 42.4 to 30.5 on the Noometry Index. Gemma 3 27B costs 5.4× less per token, which makes it the better buy when MiMo-V2-Pro's lead doesn't matter for your workload.
Which is cheaper, Gemma 3 27B or MiMo-V2-Pro?
Gemma 3 27B is cheaper. It lists at $0.08 per million input tokens and $0.16 per million output tokens; MiMo-V2-Pro lists at $0.43 and $0.87.
Is Gemma 3 27B or MiMo-V2-Pro better for coding?
MiMo-V2-Pro scores higher on coding benchmarks: 43.4 versus 22.1 in the Noometry coding category.
Which has the bigger context window?
MiMo-V2-Pro does, with 1.05M tokens against 131K.
How many benchmarks do Gemma 3 27B and MiMo-V2-Pro share?
17 benchmarks have published results for both models. Gemma 3 27B has 43 scored results on Noometry and MiMo-V2-Pro has 23.