Model comparison
Gemma 3 4B vs MiMo-V2.6-Flash
MiMo-V2.6-Flash is the stronger model overall, scoring 48.5 to 28.1 on the Noometry Index. Gemma 3 4B costs 3.5× less per token, which makes it the better buy when MiMo-V2.6-Flash's lead doesn't matter for your workload.
Last verified . 11 shared benchmarks.
GoogleSummary
- They share 11 benchmarks with published results for both. Gemma 3 4B scores higher in 0 categories and MiMo-V2.6-Flash in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where MiMo-V2.6-Flash leads 51.9 to 16.8.
- Gemma 3 4B is cheaper at $0.04 / $0.08 per million input/output tokens, against $0.14 / $0.28 for MiMo-V2.6-Flash.
- MiMo-V2.6-Flash accepts more context: 1.05M tokens versus 131K.
Side by side
| Gemma 3 4B | MiMo-V2.6-Flash | |
|---|---|---|
| Provider | Xiaomi | |
| Noometry Index | 28.1 | 48.5 |
| Released | 2025-03-12 | 2026-09-21 |
| Weights | Open | Open |
| Context window | 131K | 1.05M |
| Max output | 4K | 131K |
| Input $ / M tokens | $0.04 | $0.14 |
| Output $ / M tokens | $0.08 | $0.28 |
| Results tracked | 22 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2.6-Flash leads
Gemma 3 4B: 35.9 (#215), MiMo-V2.6-Flash: 53.4 (#30)
| Benchmark | Gemma 3 4B | MiMo-V2.6-Flash |
|---|---|---|
| LMArena Coding | 1230 | 1504 |
| LMArena WebDev | — | 1637 |
| SciCode | — | 51.3% |
Agentic & Tool Use Not comparable
Gemma 3 4B: 20.9 (#142), MiMo-V2.6-Flash: —
| Benchmark | Gemma 3 4B | MiMo-V2.6-Flash |
|---|---|---|
| Berkeley Function Calling Leaderboard | 19.6% | — |
Reasoning MiMo-V2.6-Flash leads
Gemma 3 4B: 13.2 (#335), MiMo-V2.6-Flash: 36.5 (#66)
| Benchmark | Gemma 3 4B | MiMo-V2.6-Flash |
|---|---|---|
| LMArena Hard Prompts | 1253 | 1482 |
| Kagi LLM Benchmark | 25.2% | — |
| CritPt | — | 12% |
| Chess Puzzles | 0% | — |
| DTBench | 50.9% | — |
| LMCA | 2.8% | — |
| Epoch Capabilities Index | 116.02 | — |
Math MiMo-V2.6-Flash leads
Gemma 3 4B: 16.8 (#292), MiMo-V2.6-Flash: 51.9 (#52)
| Benchmark | Gemma 3 4B | MiMo-V2.6-Flash |
|---|---|---|
| LMArena Math | 1239 | 1468 |
| OTIS Mock AIME 2024-2025 | 7.5% | — |
| ProofBench | — | 63% |
Knowledge MiMo-V2.6-Flash leads
Gemma 3 4B: 11.8 (#299), MiMo-V2.6-Flash: 42.2 (#99)
| Benchmark | Gemma 3 4B | MiMo-V2.6-Flash |
|---|---|---|
| LMArena Expert | 1223 | 1501 |
| GPQA Diamond | 23.2% | — |
| Vectara Hallucination Rate | 6.4% | — |
Multimodal Not comparable
Gemma 3 4B: —, MiMo-V2.6-Flash: 40.5 (#47)
| Benchmark | Gemma 3 4B | MiMo-V2.6-Flash |
|---|---|---|
| LMArena Vision | — | 1259 |
Multilingual MiMo-V2.6-Flash leads
Gemma 3 4B: 42.5 (#194), MiMo-V2.6-Flash: 54.0 (#51)
| Benchmark | Gemma 3 4B | MiMo-V2.6-Flash |
|---|---|---|
| LMArena Non-English | 1273 | 1434 |
| LMArena Russian | 1294 | 1409 |
| LMArena Chinese | — | 1511 |
| LMArena French | — | 1475 |
| LMArena German | 1281 | — |
| LMArena Spanish | — | 1456 |
Instruction Following MiMo-V2.6-Flash leads
Gemma 3 4B: 65.2 (#225), MiMo-V2.6-Flash: 76.8 (#35)
| Benchmark | Gemma 3 4B | MiMo-V2.6-Flash |
|---|---|---|
| LMArena Instruction Following | 1239 | 1463 |
Long Context MiMo-V2.6-Flash leads
Gemma 3 4B: 38.7 (#194), MiMo-V2.6-Flash: 44.8 (#57)
| Benchmark | Gemma 3 4B | MiMo-V2.6-Flash |
|---|---|---|
| LMArena Longer Query | 1273 | 1463 |
Writing & Preference MiMo-V2.6-Flash leads
Gemma 3 4B: 42.0 (#239), MiMo-V2.6-Flash: 63.1 (#67)
| Benchmark | Gemma 3 4B | MiMo-V2.6-Flash |
|---|---|---|
| LMArena Text | 1291 | 1455 |
| LMArena Creative Writing | 1271 | 1400 |
| LMArena Multi-Turn | 1255 | 1451 |
| EQ-Bench Creative Writing | 1068 | — |
Frequently asked questions
Is Gemma 3 4B better than MiMo-V2.6-Flash?
MiMo-V2.6-Flash is the stronger model overall, scoring 48.5 to 28.1 on the Noometry Index. Gemma 3 4B costs 3.5× less per token, which makes it the better buy when MiMo-V2.6-Flash's lead doesn't matter for your workload.
Which is cheaper, Gemma 3 4B or MiMo-V2.6-Flash?
Gemma 3 4B is cheaper. It lists at $0.04 per million input tokens and $0.08 per million output tokens; MiMo-V2.6-Flash lists at $0.14 and $0.28.
Is Gemma 3 4B or MiMo-V2.6-Flash better for coding?
MiMo-V2.6-Flash scores higher on coding benchmarks: 53.4 versus 35.9 in the Noometry coding category.
Which has the bigger context window?
MiMo-V2.6-Flash does, with 1.05M tokens against 131K.
How many benchmarks do Gemma 3 4B and MiMo-V2.6-Flash share?
11 benchmarks have published results for both models. Gemma 3 4B has 22 scored results on Noometry and MiMo-V2.6-Flash has 19.