Model comparison
MiMo-V2.5-Pro vs Step 5 Preview
Step 5 Preview is the stronger model overall, scoring 47.9 to 45.2 on the Noometry Index. MiMo-V2.5-Pro costs 2.6× less per token, which makes it the better buy when Step 5 Preview's lead doesn't matter for your workload.
Last verified . 17 shared benchmarks.
StepFunSummary
- They share 17 benchmarks with published results for both. MiMo-V2.5-Pro scores higher in 5 categories and Step 5 Preview in 3 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Step 5 Preview leads 40.0 to 26.8.
- The biggest single-benchmark swing is ProofBench: 22% for MiMo-V2.5-Pro and 42% for Step 5 Preview.
- MiMo-V2.5-Pro is cheaper at $0.43 / $0.87 per million input/output tokens, against $1 / $2.70 for Step 5 Preview.
- MiMo-V2.5-Pro accepts more context: 1.05M tokens versus 1.02M.
- MiMo-V2.5-Pro has downloadable open weights; the other is API-only.
Side by side
| MiMo-V2.5-Pro | Step 5 Preview | |
|---|---|---|
| Provider | Xiaomi | StepFun |
| Noometry Index | 45.2 | 47.9 |
| Released | 2026-04-22 | 2026-09-16 |
| Weights | Open | Proprietary |
| Context window | 1.05M | 1.02M |
| Max output | 131K | 66K |
| Input $ / M tokens | $0.43 | $1 |
| Output $ / M tokens | $0.87 | $2.70 |
| Results tracked | 27 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 5 Preview leads
MiMo-V2.5-Pro: 47.4 (#60), Step 5 Preview: 51.8 (#36)
| Benchmark | MiMo-V2.5-Pro | Step 5 Preview |
|---|---|---|
| LMArena WebDev | 1479 | 1564 |
| SciCode | 50.2% | 58.9% |
| LMArena Coding | 1503 | 1480 |
| ALE-Bench | 899.8 | — |
Reasoning Step 5 Preview leads
MiMo-V2.5-Pro: 26.8 (#130), Step 5 Preview: 40.0 (#57)
| Benchmark | MiMo-V2.5-Pro | Step 5 Preview |
|---|---|---|
| CritPt | 4% | 20.9% |
| LMArena Hard Prompts | 1488 | 1465 |
| NYT Connections (extended) | 34.4% | — |
| DTBench | 84.5% | — |
| LMCA | 29.5% | — |
Math Step 5 Preview leads
MiMo-V2.5-Pro: 40.0 (#96), Step 5 Preview: 46.1 (#72)
| Benchmark | MiMo-V2.5-Pro | Step 5 Preview |
|---|---|---|
| ProofBench | 22% | 42% |
| LMArena Math | 1481 | 1470 |
Knowledge MiMo-V2.5-Pro leads
MiMo-V2.5-Pro: 42.2 (#98), Step 5 Preview: 41.2 (#112)
| Benchmark | MiMo-V2.5-Pro | Step 5 Preview |
|---|---|---|
| LMArena Expert | 1503 | 1470 |
Multimodal Not comparable
MiMo-V2.5-Pro: —, Step 5 Preview: 41.0 (#41)
| Benchmark | MiMo-V2.5-Pro | Step 5 Preview |
|---|---|---|
| LMArena Vision | — | 1267 |
Multilingual MiMo-V2.5-Pro leads
MiMo-V2.5-Pro: 55.1 (#34), Step 5 Preview: 53.8 (#54)
| Benchmark | MiMo-V2.5-Pro | Step 5 Preview |
|---|---|---|
| LMArena Non-English | 1449 | 1432 |
| LMArena Chinese | 1507 | 1519 |
| LMArena Russian | 1450 | 1436 |
| LMArena Spanish | 1471 | 1439 |
| LMArena French | 1488 | — |
| LMArena German | 1458 | — |
| LMArena Japanese | 1412 | — |
| LMArena Korean | 1437 | — |
Instruction Following MiMo-V2.5-Pro leads
MiMo-V2.5-Pro: 77.5 (#21), Step 5 Preview: 76.0 (#50)
| Benchmark | MiMo-V2.5-Pro | Step 5 Preview |
|---|---|---|
| LMArena Instruction Following | 1477 | 1444 |
Long Context Too close to call
MiMo-V2.5-Pro: 45.4 (#37), Step 5 Preview: 44.5 (#64)
| Benchmark | MiMo-V2.5-Pro | Step 5 Preview |
|---|---|---|
| LMArena Longer Query | 1483 | 1455 |
Writing & Preference MiMo-V2.5-Pro leads
MiMo-V2.5-Pro: 65.3 (#49), Step 5 Preview: 62.8 (#71)
| Benchmark | MiMo-V2.5-Pro | Step 5 Preview |
|---|---|---|
| LMArena Text | 1465 | 1442 |
| LMArena Creative Writing | 1440 | 1410 |
| LMArena Multi-Turn | 1477 | 1447 |
| EQ-Bench Creative Writing | 1493 | — |
| EQ-Bench 4 | 1208 | — |
Frequently asked questions
Is MiMo-V2.5-Pro better than Step 5 Preview?
Step 5 Preview is the stronger model overall, scoring 47.9 to 45.2 on the Noometry Index. MiMo-V2.5-Pro costs 2.6× less per token, which makes it the better buy when Step 5 Preview's lead doesn't matter for your workload.
Which is cheaper, MiMo-V2.5-Pro or Step 5 Preview?
MiMo-V2.5-Pro is cheaper. It lists at $0.43 per million input tokens and $0.87 per million output tokens; Step 5 Preview lists at $1 and $2.70.
Is MiMo-V2.5-Pro or Step 5 Preview better for coding?
Step 5 Preview scores higher on coding benchmarks: 51.8 versus 47.4 in the Noometry coding category.
Which has the bigger context window?
MiMo-V2.5-Pro does, with 1.05M tokens against 1.02M.
How many benchmarks do MiMo-V2.5-Pro and Step 5 Preview share?
17 benchmarks have published results for both models. MiMo-V2.5-Pro has 27 scored results on Noometry and Step 5 Preview has 18.