Model comparison
Granite 4.0 Micro vs MiMo-V2.5-Pro
MiMo-V2.5-Pro is the stronger model overall, scoring 44.8 to 28.8 on the Noometry Index. Granite 4.0 Micro costs 13× less per token, which makes it the better buy when MiMo-V2.5-Pro's lead doesn't matter for your workload.
Last verified . 0 shared benchmarks.
Summary
- The widest gap is in knowledge, where MiMo-V2.5-Pro leads 41.5 to 9.9.
- Granite 4.0 Micro is cheaper at $0.017 / $0.11 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
| Granite 4.0 Micro | MiMo-V2.5-Pro | |
|---|---|---|
| Provider | IBM | Xiaomi |
| Noometry Index | 28.8 | 44.8 |
| Released | 2025-10-02 | 2026-04-22 |
| Weights | Open | Open |
| Context window | 131K | 1.05M |
| Max output | 118K | 131K |
| Input $ / M tokens | $0.017 | $0.43 |
| Output $ / M tokens | $0.11 | $0.87 |
| Results tracked | 8 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Granite 4.0 Micro: —, MiMo-V2.5-Pro: 47.0 (#58)
| Benchmark | Granite 4.0 Micro | MiMo-V2.5-Pro |
|---|---|---|
| LMArena WebDev | — | 1477 |
| SciCode | — | 50.2% |
| LMArena Coding | — | 1502 |
| ALE-Bench | — | 899.8 |
Reasoning MiMo-V2.5-Pro leads
Granite 4.0 Micro: 18.5 (#261), MiMo-V2.5-Pro: 25.9 (#124)
| Benchmark | Granite 4.0 Micro | MiMo-V2.5-Pro |
|---|---|---|
| NYT Connections (extended) | — | 34.4% |
| CritPt | — | 4% |
| Chess Puzzles | 0% | — |
| LMArena Hard Prompts | — | 1487 |
| DTBench | — | 84.5% |
| LMCA | — | 29.5% |
Math MiMo-V2.5-Pro leads
Granite 4.0 Micro: 11.2 (#301), MiMo-V2.5-Pro: 38.6 (#84)
| Benchmark | Granite 4.0 Micro | MiMo-V2.5-Pro |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.8% | — |
| ProofBench | — | 22% |
| Omni-MATH | 20.9% | — |
| LMArena Math | — | 1480 |
Knowledge MiMo-V2.5-Pro leads
Granite 4.0 Micro: 9.9 (#299), MiMo-V2.5-Pro: 41.5 (#100)
| Benchmark | Granite 4.0 Micro | MiMo-V2.5-Pro |
|---|---|---|
| GPQA Diamond | 28.3% | — |
| MMLU-Pro | 39.5% | — |
| GPQA (HELM) | 30.7% | — |
| LMArena Expert | — | 1501 |
Multilingual Not comparable
Granite 4.0 Micro: —, MiMo-V2.5-Pro: 55.3 (#33)
| Benchmark | Granite 4.0 Micro | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Non-English | — | 1449 |
| LMArena Chinese | — | 1507 |
| LMArena French | — | 1489 |
| LMArena German | — | 1455 |
| LMArena Japanese | — | 1418 |
| LMArena Korean | — | 1436 |
| LMArena Russian | — | 1450 |
| LMArena Spanish | — | 1470 |
Instruction Following MiMo-V2.5-Pro leads
Granite 4.0 Micro: 70.0 (#164), MiMo-V2.5-Pro: 77.6 (#21)
| Benchmark | Granite 4.0 Micro | MiMo-V2.5-Pro |
|---|---|---|
| IFEval | 84.9% | — |
| LMArena Instruction Following | — | 1477 |
Long Context Not comparable
Granite 4.0 Micro: —, MiMo-V2.5-Pro: 45.4 (#38)
| Benchmark | Granite 4.0 Micro | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Longer Query | — | 1482 |
Writing & Preference MiMo-V2.5-Pro leads
Granite 4.0 Micro: 46.7 (#212), MiMo-V2.5-Pro: 65.5 (#47)
| Benchmark | Granite 4.0 Micro | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Text | — | 1465 |
| LMArena Creative Writing | — | 1440 |
| EQ-Bench Creative Writing | — | 1493 |
| WildBench | 67% | — |
| EQ-Bench 4 | — | 1208 |
| LMArena Multi-Turn | — | 1477 |
Frequently asked questions
Is Granite 4.0 Micro better than MiMo-V2.5-Pro?
MiMo-V2.5-Pro is the stronger model overall, scoring 44.8 to 28.8 on the Noometry Index. Granite 4.0 Micro costs 13× 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, Granite 4.0 Micro or MiMo-V2.5-Pro?
Granite 4.0 Micro is cheaper. It lists at $0.017 per million input tokens and $0.11 per million output tokens; MiMo-V2.5-Pro lists at $0.43 and $0.87.
Which has the bigger context window?
MiMo-V2.5-Pro does, with 1.05M tokens against 131K.
How many benchmarks do Granite 4.0 Micro and MiMo-V2.5-Pro share?
0 benchmarks have published results for both models. Granite 4.0 Micro has 8 scored results on Noometry and MiMo-V2.5-Pro has 27.