Model comparison
Gemma 3 4B vs MiMo-V2.5-Pro
MiMo-V2.5-Pro is the stronger model overall, scoring 45.2 to 28.1 on the Noometry Index. Gemma 3 4B costs 11× less per token, which makes it the better buy when MiMo-V2.5-Pro's lead doesn't matter for your workload.
Last verified . 15 shared benchmarks.
GoogleSummary
- They share 15 benchmarks with published results for both. Gemma 3 4B 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 knowledge, where MiMo-V2.5-Pro leads 42.2 to 11.8.
- The biggest single-benchmark swing is DTBench: 50.9% for Gemma 3 4B and 84.5% for MiMo-V2.5-Pro.
- Gemma 3 4B is cheaper at $0.04 / $0.08 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 4B | MiMo-V2.5-Pro | |
|---|---|---|
| Provider | Xiaomi | |
| Noometry Index | 28.1 | 45.2 |
| Released | 2025-03-12 | 2026-04-22 |
| Weights | Open | Open |
| Context window | 131K | 1.05M |
| Max output | 4K | 131K |
| Input $ / M tokens | $0.04 | $0.43 |
| Output $ / M tokens | $0.08 | $0.87 |
| Results tracked | 22 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2.5-Pro leads
Gemma 3 4B: 35.9 (#215), MiMo-V2.5-Pro: 47.4 (#60)
| Benchmark | Gemma 3 4B | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Coding | 1230 | 1503 |
| LMArena WebDev | — | 1479 |
| SciCode | — | 50.2% |
| ALE-Bench | — | 899.8 |
Agentic & Tool Use Not comparable
Gemma 3 4B: 20.9 (#142), MiMo-V2.5-Pro: —
| Benchmark | Gemma 3 4B | MiMo-V2.5-Pro |
|---|---|---|
| Berkeley Function Calling Leaderboard | 19.6% | — |
Reasoning MiMo-V2.5-Pro leads
Gemma 3 4B: 13.2 (#335), MiMo-V2.5-Pro: 26.8 (#130)
| Benchmark | Gemma 3 4B | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Hard Prompts | 1253 | 1488 |
| DTBench | 50.9% | 84.5% |
| LMCA | 2.8% | 29.5% |
| Kagi LLM Benchmark | 25.2% | — |
| NYT Connections (extended) | — | 34.4% |
| CritPt | — | 4% |
| Chess Puzzles | 0% | — |
| Epoch Capabilities Index | 116.02 | — |
Math MiMo-V2.5-Pro leads
Gemma 3 4B: 16.8 (#292), MiMo-V2.5-Pro: 40.0 (#96)
| Benchmark | Gemma 3 4B | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Math | 1239 | 1481 |
| OTIS Mock AIME 2024-2025 | 7.5% | — |
| ProofBench | — | 22% |
Knowledge MiMo-V2.5-Pro leads
Gemma 3 4B: 11.8 (#299), MiMo-V2.5-Pro: 42.2 (#98)
| Benchmark | Gemma 3 4B | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Expert | 1223 | 1503 |
| GPQA Diamond | 23.2% | — |
| Vectara Hallucination Rate | 6.4% | — |
Multilingual MiMo-V2.5-Pro leads
Gemma 3 4B: 42.5 (#194), MiMo-V2.5-Pro: 55.1 (#34)
| Benchmark | Gemma 3 4B | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Non-English | 1273 | 1449 |
| LMArena German | 1281 | 1458 |
| LMArena Russian | 1294 | 1450 |
| LMArena Chinese | — | 1507 |
| LMArena French | — | 1488 |
| LMArena Japanese | — | 1412 |
| LMArena Korean | — | 1437 |
| LMArena Spanish | — | 1471 |
Instruction Following MiMo-V2.5-Pro leads
Gemma 3 4B: 65.2 (#225), MiMo-V2.5-Pro: 77.5 (#21)
| Benchmark | Gemma 3 4B | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Instruction Following | 1239 | 1477 |
Long Context MiMo-V2.5-Pro leads
Gemma 3 4B: 38.7 (#194), MiMo-V2.5-Pro: 45.4 (#37)
| Benchmark | Gemma 3 4B | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Longer Query | 1273 | 1483 |
Writing & Preference MiMo-V2.5-Pro leads
Gemma 3 4B: 42.0 (#239), MiMo-V2.5-Pro: 65.3 (#49)
| Benchmark | Gemma 3 4B | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Text | 1291 | 1465 |
| LMArena Creative Writing | 1271 | 1440 |
| EQ-Bench Creative Writing | 1068 | 1493 |
| LMArena Multi-Turn | 1255 | 1477 |
| EQ-Bench 4 | — | 1208 |
Frequently asked questions
Is Gemma 3 4B better than MiMo-V2.5-Pro?
MiMo-V2.5-Pro is the stronger model overall, scoring 45.2 to 28.1 on the Noometry Index. Gemma 3 4B costs 11× 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 4B or MiMo-V2.5-Pro?
Gemma 3 4B is cheaper. It lists at $0.04 per million input tokens and $0.08 per million output tokens; MiMo-V2.5-Pro lists at $0.43 and $0.87.
Is Gemma 3 4B or MiMo-V2.5-Pro better for coding?
MiMo-V2.5-Pro scores higher on coding benchmarks: 47.4 versus 35.9 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 4B and MiMo-V2.5-Pro share?
15 benchmarks have published results for both models. Gemma 3 4B has 22 scored results on Noometry and MiMo-V2.5-Pro has 27.