Model comparison
Gemma 2 27B vs MiMo-V2.5-Pro
MiMo-V2.5-Pro is the stronger model overall, scoring 45.2 to 29.4 on the Noometry Index.
Last verified . 19 shared benchmarks.
GoogleSummary
- They share 19 benchmarks with published results for both. Gemma 2 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 math, where MiMo-V2.5-Pro leads 40.0 to 10.7.
- The biggest single-benchmark swing is DTBench: 48% for Gemma 2 27B and 84.5% for MiMo-V2.5-Pro.
- MiMo-V2.5-Pro is cheaper at $0.43 / $0.87 per million input/output tokens, against $0.65 / $0.65 for Gemma 2 27B.
- MiMo-V2.5-Pro accepts more context: 1.05M tokens versus 8K.
Side by side
| Gemma 2 27B | MiMo-V2.5-Pro | |
|---|---|---|
| Provider | Xiaomi | |
| Noometry Index | 29.4 | 45.2 |
| Released | 2024-06-24 | 2026-04-22 |
| Weights | Open | Open |
| Context window | 8K | 1.05M |
| Max output | 2K | 131K |
| Input $ / M tokens | $0.65 | $0.43 |
| Output $ / M tokens | $0.65 | $0.87 |
| Results tracked | 34 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2.5-Pro leads
Gemma 2 27B: 34.1 (#246), MiMo-V2.5-Pro: 47.4 (#60)
| Benchmark | Gemma 2 27B | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Coding | 1211 | 1503 |
| LMArena WebDev | — | 1479 |
| SciCode | — | 50.2% |
| BigCodeBench Instruct | 42.8% | — |
| LiveBench Coding | 36% | — |
| BigCodeBench Complete | 52.5% | — |
| ALE-Bench | — | 899.8 |
Reasoning MiMo-V2.5-Pro leads
Gemma 2 27B: 15.3 (#315), MiMo-V2.5-Pro: 26.8 (#130)
| Benchmark | Gemma 2 27B | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Hard Prompts | 1198 | 1488 |
| DTBench | 48% | 84.5% |
| LMCA | 7.1% | 29.5% |
| NYT Connections (extended) | — | 34.4% |
| CritPt | — | 4% |
| LiveBench Reasoning | 28.1% | — |
| LiveBench Data Analysis | 47.9% | — |
| Epoch Capabilities Index | 122.08 | — |
| LiveBench | 38.2% | — |
Math MiMo-V2.5-Pro leads
Gemma 2 27B: 10.7 (#311), MiMo-V2.5-Pro: 40.0 (#96)
| Benchmark | Gemma 2 27B | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Math | 1212 | 1481 |
| OTIS Mock AIME 2024-2025 | 1.4% | — |
| ProofBench | — | 22% |
| LiveBench Math | 26.5% | — |
| MATH Level 5 | 27.9% | — |
Knowledge MiMo-V2.5-Pro leads
Gemma 2 27B: 19.0 (#280), MiMo-V2.5-Pro: 42.2 (#98)
| Benchmark | Gemma 2 27B | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Expert | 1172 | 1503 |
| GPQA Diamond | 36.5% | — |
| Confabulations | 27.1% | — |
| MMLU | 75.7% | — |
Multilingual MiMo-V2.5-Pro leads
Gemma 2 27B: 38.6 (#226), MiMo-V2.5-Pro: 55.1 (#34)
| Benchmark | Gemma 2 27B | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Non-English | 1217 | 1449 |
| LMArena Chinese | 1221 | 1507 |
| LMArena French | 1247 | 1488 |
| LMArena German | 1209 | 1458 |
| LMArena Japanese | 1175 | 1412 |
| LMArena Korean | 1174 | 1437 |
| LMArena Russian | 1234 | 1450 |
| LMArena Spanish | 1228 | 1471 |
Instruction Following MiMo-V2.5-Pro leads
Gemma 2 27B: 60.5 (#249), MiMo-V2.5-Pro: 77.5 (#21)
| Benchmark | Gemma 2 27B | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Instruction Following | 1206 | 1477 |
| LiveBench Instruction Following | 58.1% | — |
Long Context MiMo-V2.5-Pro leads
Gemma 2 27B: 37.3 (#218), MiMo-V2.5-Pro: 45.4 (#37)
| Benchmark | Gemma 2 27B | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Longer Query | 1231 | 1483 |
Writing & Preference MiMo-V2.5-Pro leads
Gemma 2 27B: 44.2 (#225), MiMo-V2.5-Pro: 65.3 (#49)
| Benchmark | Gemma 2 27B | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Text | 1231 | 1465 |
| LMArena Creative Writing | 1241 | 1440 |
| LMArena Multi-Turn | 1224 | 1477 |
| EQ-Bench Creative Writing | — | 1493 |
| EQ-Bench 4 | — | 1208 |
| LiveBench Language | 32.6% | — |
Frequently asked questions
Is Gemma 2 27B better than MiMo-V2.5-Pro?
MiMo-V2.5-Pro is the stronger model overall, scoring 45.2 to 29.4 on the Noometry Index.
Which is cheaper, Gemma 2 27B or MiMo-V2.5-Pro?
MiMo-V2.5-Pro is cheaper. It lists at $0.43 per million input tokens and $0.87 per million output tokens; Gemma 2 27B lists at $0.65 and $0.65.
Is Gemma 2 27B or MiMo-V2.5-Pro better for coding?
MiMo-V2.5-Pro scores higher on coding benchmarks: 47.4 versus 34.1 in the Noometry coding category.
Which has the bigger context window?
MiMo-V2.5-Pro does, with 1.05M tokens against 8K.
How many benchmarks do Gemma 2 27B and MiMo-V2.5-Pro share?
19 benchmarks have published results for both models. Gemma 2 27B has 34 scored results on Noometry and MiMo-V2.5-Pro has 27.