Model comparison
Gemma 3 27B vs MiMo-V2.5-Pro
MiMo-V2.5-Pro is the stronger model overall, scoring 45.2 to 30.8 on the Noometry Index. Gemma 3 27B costs 5.4× less per token, which makes it the better buy when MiMo-V2.5-Pro's lead doesn't matter for your workload.
Last verified . 22 shared benchmarks.
GoogleSummary
- They share 22 benchmarks with published results for both. Gemma 3 27B scores higher in 0 categories and MiMo-V2.5-Pro in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where MiMo-V2.5-Pro leads 47.4 to 22.5.
- The biggest single-benchmark swing is DTBench: 52.5% for Gemma 3 27B and 84.5% for MiMo-V2.5-Pro.
- Gemma 3 27B is cheaper at $0.08 / $0.16 per million input/output tokens, against $0.43 / $0.87 for MiMo-V2.5-Pro.
- MiMo-V2.5-Pro accepts more context: 1.05M tokens versus 131K.
Side by side
| Gemma 3 27B | MiMo-V2.5-Pro | |
|---|---|---|
| Provider | Xiaomi | |
| Noometry Index | 30.8 | 45.2 |
| Released | 2025-03-11 | 2026-04-22 |
| Weights | Open | Open |
| 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 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2.5-Pro leads
Gemma 3 27B: 22.5 (#334), MiMo-V2.5-Pro: 47.4 (#60)
| Benchmark | Gemma 3 27B | MiMo-V2.5-Pro |
|---|---|---|
| SciCode | 21.2% | 50.2% |
| LMArena Coding | 1322 | 1503 |
| Aider Polyglot | 4.9% | — |
| LMArena WebDev | — | 1479 |
| LiveBench Coding | 39.9% | — |
| ALE-Bench | — | 899.8 |
Agentic & Tool Use Not comparable
Gemma 3 27B: 25.1 (#110), MiMo-V2.5-Pro: —
| Benchmark | Gemma 3 27B | MiMo-V2.5-Pro |
|---|---|---|
| Berkeley Function Calling Leaderboard | 29.5% | — |
Reasoning MiMo-V2.5-Pro leads
Gemma 3 27B: 16.7 (#301), MiMo-V2.5-Pro: 26.8 (#130)
| Benchmark | Gemma 3 27B | MiMo-V2.5-Pro |
|---|---|---|
| CritPt | 0% | 4% |
| LMArena Hard Prompts | 1340 | 1488 |
| DTBench | 52.5% | 84.5% |
| LMCA | 12.3% | 29.5% |
| Kagi LLM Benchmark | 40.4% | — |
| NYT Connections (extended) | — | 34.4% |
| Chess Puzzles | 0% | — |
| LiveBench Reasoning | 43.8% | — |
| LiveBench Data Analysis | 51.5% | — |
| Epoch Capabilities Index | 130.04 | — |
| LiveBench | 50% | — |
Math MiMo-V2.5-Pro leads
Gemma 3 27B: 25.9 (#265), MiMo-V2.5-Pro: 40.0 (#96)
| Benchmark | Gemma 3 27B | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Math | 1312 | 1481 |
| OTIS Mock AIME 2024-2025 | 22.5% | — |
| ProofBench | — | 22% |
| LiveBench Math | 55.4% | — |
| MATH Level 5 | 74% | — |
Knowledge MiMo-V2.5-Pro leads
Gemma 3 27B: 25.5 (#261), MiMo-V2.5-Pro: 42.2 (#98)
| Benchmark | Gemma 3 27B | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Expert | 1304 | 1503 |
| GPQA Diamond | 47.7% | — |
| Confabulations | 40.3% | — |
| Vectara Hallucination Rate | 7.4% | — |
Multimodal Not comparable
Gemma 3 27B: 32.6 (#100), MiMo-V2.5-Pro: —
| Benchmark | Gemma 3 27B | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Vision | 1164 | — |
| GeoBench | 52% | — |
Multilingual MiMo-V2.5-Pro leads
Gemma 3 27B: 46.9 (#155), MiMo-V2.5-Pro: 55.1 (#34)
| Benchmark | Gemma 3 27B | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Non-English | 1334 | 1449 |
| LMArena Chinese | 1346 | 1507 |
| LMArena French | 1368 | 1488 |
| LMArena German | 1362 | 1458 |
| LMArena Japanese | 1287 | 1412 |
| LMArena Korean | 1308 | 1437 |
| LMArena Russian | 1349 | 1450 |
| LMArena Spanish | 1349 | 1471 |
Instruction Following MiMo-V2.5-Pro leads
Gemma 3 27B: 70.6 (#160), MiMo-V2.5-Pro: 77.5 (#21)
| Benchmark | Gemma 3 27B | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Instruction Following | 1321 | 1477 |
| LiveBench Instruction Following | 74.9% | — |
Long Context MiMo-V2.5-Pro leads
Gemma 3 27B: 27.6 (#293), MiMo-V2.5-Pro: 45.4 (#37)
| Benchmark | Gemma 3 27B | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Longer Query | 1333 | 1483 |
| Fiction.LiveBench | 33.3% | — |
Writing & Preference MiMo-V2.5-Pro leads
Gemma 3 27B: 52.5 (#168), MiMo-V2.5-Pro: 65.3 (#49)
| Benchmark | Gemma 3 27B | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Text | 1358 | 1465 |
| LMArena Creative Writing | 1346 | 1440 |
| EQ-Bench Creative Writing | 1266 | 1493 |
| LMArena Multi-Turn | 1345 | 1477 |
| Short-Story Creative Writing | 79.9% | — |
| EQ-Bench 4 | — | 1208 |
| LiveBench Language | 34.6% | — |
Frequently asked questions
Is Gemma 3 27B better than MiMo-V2.5-Pro?
MiMo-V2.5-Pro is the stronger model overall, scoring 45.2 to 30.8 on the Noometry Index. Gemma 3 27B costs 5.4× less per token, which makes it the better buy when MiMo-V2.5-Pro's lead doesn't matter for your workload.
Which is cheaper, Gemma 3 27B or MiMo-V2.5-Pro?
Gemma 3 27B is cheaper. It lists at $0.08 per million input tokens and $0.16 per million output tokens; MiMo-V2.5-Pro lists at $0.43 and $0.87.
Is Gemma 3 27B or MiMo-V2.5-Pro better for coding?
MiMo-V2.5-Pro scores higher on coding benchmarks: 47.4 versus 22.5 in the Noometry coding category.
Which has the bigger context window?
MiMo-V2.5-Pro does, with 1.05M tokens against 131K.
How many benchmarks do Gemma 3 27B and MiMo-V2.5-Pro share?
22 benchmarks have published results for both models. Gemma 3 27B has 43 scored results on Noometry and MiMo-V2.5-Pro has 27.