Model comparison
Gemma 3 12B vs MiMo-V2.5-Pro
MiMo-V2.5-Pro is the stronger model overall, scoring 44.8 to 31.8 on the Noometry Index. Gemma 3 12B costs 7.2× less per token, which makes it the better buy when MiMo-V2.5-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 12B 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 writing & preference, where MiMo-V2.5-Pro leads 65.5 to 47.7.
- The biggest single-benchmark swing is DTBench: 48.8% for Gemma 3 12B and 84.5% for MiMo-V2.5-Pro.
- Gemma 3 12B is cheaper at $0.05 / $0.15 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 12B | MiMo-V2.5-Pro | |
|---|---|---|
| Provider | Xiaomi | |
| Noometry Index | 31.8 | 44.8 |
| Released | 2025-03-12 | 2026-04-22 |
| Weights | Open | Open |
| Context window | 131K | 1.05M |
| Max output | 8K | 131K |
| Input $ / M tokens | $0.05 | $0.43 |
| Output $ / M tokens | $0.15 | $0.87 |
| Results tracked | 24 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2.5-Pro leads
Gemma 3 12B: 31.2 (#276), MiMo-V2.5-Pro: 47.0 (#58)
| Benchmark | Gemma 3 12B | MiMo-V2.5-Pro |
|---|---|---|
| SciCode | 17.4% | 50.2% |
| LMArena Coding | 1281 | 1502 |
| LMArena WebDev | — | 1477 |
| ALE-Bench | — | 899.8 |
Agentic & Tool Use Not comparable
Gemma 3 12B: 25.3 (#101), MiMo-V2.5-Pro: —
| Benchmark | Gemma 3 12B | MiMo-V2.5-Pro |
|---|---|---|
| Berkeley Function Calling Leaderboard | 30.4% | — |
Reasoning MiMo-V2.5-Pro leads
Gemma 3 12B: 15.2 (#307), MiMo-V2.5-Pro: 25.9 (#124)
| Benchmark | Gemma 3 12B | MiMo-V2.5-Pro |
|---|---|---|
| CritPt | 0% | 4% |
| LMArena Hard Prompts | 1309 | 1487 |
| DTBench | 48.8% | 84.5% |
| LMCA | 4.5% | 29.5% |
| NYT Connections (extended) | — | 34.4% |
| Chess Puzzles | 0% | — |
| Epoch Capabilities Index | 123.49 | — |
Math MiMo-V2.5-Pro leads
Gemma 3 12B: 21.0 (#273), MiMo-V2.5-Pro: 38.6 (#84)
| Benchmark | Gemma 3 12B | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Math | 1307 | 1480 |
| OTIS Mock AIME 2024-2025 | 16.7% | — |
| ProofBench | — | 22% |
Knowledge MiMo-V2.5-Pro leads
Gemma 3 12B: 26.5 (#250), MiMo-V2.5-Pro: 41.5 (#100)
| Benchmark | Gemma 3 12B | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Expert | 1248 | 1501 |
| GPQA Diamond | 39.5% | — |
| Vectara Hallucination Rate | 4.4% | — |
Multimodal Not comparable
Gemma 3 12B: —, MiMo-V2.5-Pro: —
| Benchmark | Gemma 3 12B | MiMo-V2.5-Pro |
|---|---|---|
| MindCube | 46.7% | — |
Multilingual MiMo-V2.5-Pro leads
Gemma 3 12B: 45.9 (#160), MiMo-V2.5-Pro: 55.3 (#33)
| Benchmark | Gemma 3 12B | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Non-English | 1318 | 1449 |
| LMArena German | 1370 | 1455 |
| LMArena Russian | 1335 | 1450 |
| LMArena Chinese | — | 1507 |
| LMArena French | — | 1489 |
| LMArena Japanese | — | 1418 |
| LMArena Korean | — | 1436 |
| LMArena Spanish | — | 1470 |
Instruction Following MiMo-V2.5-Pro leads
Gemma 3 12B: 68.8 (#179), MiMo-V2.5-Pro: 77.6 (#21)
| Benchmark | Gemma 3 12B | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Instruction Following | 1299 | 1477 |
Long Context MiMo-V2.5-Pro leads
Gemma 3 12B: 40.0 (#157), MiMo-V2.5-Pro: 45.4 (#38)
| Benchmark | Gemma 3 12B | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Longer Query | 1317 | 1482 |
Writing & Preference MiMo-V2.5-Pro leads
Gemma 3 12B: 47.7 (#205), MiMo-V2.5-Pro: 65.5 (#47)
| Benchmark | Gemma 3 12B | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Text | 1334 | 1465 |
| LMArena Creative Writing | 1331 | 1440 |
| EQ-Bench Creative Writing | 1126 | 1493 |
| LMArena Multi-Turn | 1334 | 1477 |
| EQ-Bench 4 | — | 1208 |
Frequently asked questions
Is Gemma 3 12B better than MiMo-V2.5-Pro?
MiMo-V2.5-Pro is the stronger model overall, scoring 44.8 to 31.8 on the Noometry Index. Gemma 3 12B costs 7.2× 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 12B or MiMo-V2.5-Pro?
Gemma 3 12B is cheaper. It lists at $0.05 per million input tokens and $0.15 per million output tokens; MiMo-V2.5-Pro lists at $0.43 and $0.87.
Is Gemma 3 12B or MiMo-V2.5-Pro better for coding?
MiMo-V2.5-Pro scores higher on coding benchmarks: 47.0 versus 31.2 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 12B and MiMo-V2.5-Pro share?
17 benchmarks have published results for both models. Gemma 3 12B has 24 scored results on Noometry and MiMo-V2.5-Pro has 27.