Model comparison
Gemma 4 26B A4B IT vs MiMo-V2.5-Pro
MiMo-V2.5-Pro is the stronger model overall, scoring 44.8 to 43.1 on the Noometry Index. Gemma 4 26B A4B IT costs 4.5× less per token, which makes it the better buy when MiMo-V2.5-Pro's lead doesn't matter for your workload.
Last verified . 21 shared benchmarks.
GoogleSummary
- They share 21 benchmarks with published results for both. Gemma 4 26B A4B IT scores higher in 2 categories and MiMo-V2.5-Pro in 6 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where MiMo-V2.5-Pro leads 47.0 to 38.8.
- The biggest single-benchmark swing is SciCode: 40% for Gemma 4 26B A4B IT and 50.2% for MiMo-V2.5-Pro.
- Gemma 4 26B A4B IT is cheaper at $0.0765 / $0.26 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 262K.
Side by side
| Gemma 4 26B A4B IT | MiMo-V2.5-Pro | |
|---|---|---|
| Provider | Xiaomi | |
| Noometry Index | 43.1 | 44.8 |
| Released | 2026-04-02 | 2026-04-22 |
| Weights | Open | Open |
| Context window | 262K | 1.05M |
| Max output | 33K | 131K |
| Input $ / M tokens | $0.0765 | $0.43 |
| Output $ / M tokens | $0.26 | $0.87 |
| Results tracked | 28 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2.5-Pro leads
Gemma 4 26B A4B IT: 38.8 (#156), MiMo-V2.5-Pro: 47.0 (#58)
| Benchmark | Gemma 4 26B A4B IT | MiMo-V2.5-Pro |
|---|---|---|
| LMArena WebDev | 1359 | 1477 |
| SciCode | 40% | 50.2% |
| LMArena Coding | 1446 | 1502 |
| ALE-Bench | 927.17 | 899.8 |
| WeirdML | 35.2% | — |
Reasoning MiMo-V2.5-Pro leads
Gemma 4 26B A4B IT: 21.1 (#205), MiMo-V2.5-Pro: 25.9 (#124)
| Benchmark | Gemma 4 26B A4B IT | MiMo-V2.5-Pro |
|---|---|---|
| CritPt | 0% | 4% |
| LMArena Hard Prompts | 1438 | 1487 |
| DTBench | 74.9% | 84.5% |
| LMCA | 29.7% | 29.5% |
| NYT Connections (extended) | — | 34.4% |
| Chess Puzzles | 6% | — |
| Epoch Capabilities Index | 141.85 | — |
Math Gemma 4 26B A4B IT leads
Gemma 4 26B A4B IT: 45.7 (#61), MiMo-V2.5-Pro: 38.6 (#84)
| Benchmark | Gemma 4 26B A4B IT | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Math | 1469 | 1480 |
| OTIS Mock AIME 2024-2025 | 82.2% | — |
| ProofBench | — | 22% |
Knowledge Gemma 4 26B A4B IT leads
Gemma 4 26B A4B IT: 45.6 (#79), MiMo-V2.5-Pro: 41.5 (#100)
| Benchmark | Gemma 4 26B A4B IT | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Expert | 1447 | 1501 |
| GPQA Diamond | 73.2% | — |
| Vectara Hallucination Rate | 5.2% | — |
Multimodal Not comparable
Gemma 4 26B A4B IT: 39.9 (#43), MiMo-V2.5-Pro: —
| Benchmark | Gemma 4 26B A4B IT | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Vision | 1260 | — |
Multilingual MiMo-V2.5-Pro leads
Gemma 4 26B A4B IT: 53.3 (#68), MiMo-V2.5-Pro: 55.3 (#33)
| Benchmark | Gemma 4 26B A4B IT | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Non-English | 1422 | 1449 |
| LMArena Chinese | 1495 | 1507 |
| LMArena French | 1459 | 1489 |
| LMArena Russian | 1434 | 1450 |
| LMArena Spanish | 1415 | 1470 |
| LMArena German | — | 1455 |
| LMArena Japanese | — | 1418 |
| LMArena Korean | — | 1436 |
Instruction Following MiMo-V2.5-Pro leads
Gemma 4 26B A4B IT: 75.0 (#78), MiMo-V2.5-Pro: 77.6 (#21)
| Benchmark | Gemma 4 26B A4B IT | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Instruction Following | 1420 | 1477 |
Long Context MiMo-V2.5-Pro leads
Gemma 4 26B A4B IT: 43.6 (#87), MiMo-V2.5-Pro: 45.4 (#38)
| Benchmark | Gemma 4 26B A4B IT | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Longer Query | 1427 | 1482 |
Writing & Preference MiMo-V2.5-Pro leads
Gemma 4 26B A4B IT: 58.8 (#110), MiMo-V2.5-Pro: 65.5 (#47)
| Benchmark | Gemma 4 26B A4B IT | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Text | 1434 | 1465 |
| LMArena Creative Writing | 1401 | 1440 |
| EQ-Bench Creative Writing | 1305 | 1493 |
| LMArena Multi-Turn | 1442 | 1477 |
| EQ-Bench 4 | — | 1208 |
Frequently asked questions
Is Gemma 4 26B A4B IT better than MiMo-V2.5-Pro?
MiMo-V2.5-Pro is the stronger model overall, scoring 44.8 to 43.1 on the Noometry Index. Gemma 4 26B A4B IT costs 4.5× 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 4 26B A4B IT or MiMo-V2.5-Pro?
Gemma 4 26B A4B IT is cheaper. It lists at $0.0765 per million input tokens and $0.26 per million output tokens; MiMo-V2.5-Pro lists at $0.43 and $0.87.
Is Gemma 4 26B A4B IT or MiMo-V2.5-Pro better for coding?
MiMo-V2.5-Pro scores higher on coding benchmarks: 47.0 versus 38.8 in the Noometry coding category.
Which has the bigger context window?
MiMo-V2.5-Pro does, with 1.05M tokens against 262K.
How many benchmarks do Gemma 4 26B A4B IT and MiMo-V2.5-Pro share?
21 benchmarks have published results for both models. Gemma 4 26B A4B IT has 28 scored results on Noometry and MiMo-V2.5-Pro has 27.