Model comparison
MiMo-V2.5-Pro vs Step 3
MiMo-V2.5-Pro is the stronger model overall, scoring 44.8 to 39.9 on the Noometry Index.
Last verified . 15 shared benchmarks.
StepFunSummary
- They share 15 benchmarks with published results for both. MiMo-V2.5-Pro scores higher in 7 categories and Step 3 in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiMo-V2.5-Pro leads 65.5 to 54.5.
Side by side
| MiMo-V2.5-Pro | Step 3 | |
|---|---|---|
| Provider | Xiaomi | StepFun |
| Noometry Index | 44.8 | 39.9 |
| Released | 2026-04-22 | — |
| Weights | Open | Open |
| Context window | 1.05M | — |
| Max output | 131K | — |
| Input $ / M tokens | $0.43 | — |
| Output $ / M tokens | $0.87 | — |
| Results tracked | 27 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2.5-Pro leads
MiMo-V2.5-Pro: 47.0 (#58), Step 3: 39.5 (#144)
| Benchmark | MiMo-V2.5-Pro | Step 3 |
|---|---|---|
| LMArena Coding | 1502 | 1367 |
| LMArena WebDev | 1477 | — |
| SciCode | 50.2% | — |
| ALE-Bench | 899.8 | — |
Reasoning Step 3 leads
MiMo-V2.5-Pro: 25.9 (#124), Step 3: 27.6 (#102)
| Benchmark | MiMo-V2.5-Pro | Step 3 |
|---|---|---|
| LMArena Hard Prompts | 1487 | 1355 |
| Kagi LLM Benchmark | — | 62.3% |
| NYT Connections (extended) | 34.4% | — |
| CritPt | 4% | — |
| DTBench | 84.5% | — |
| LMCA | 29.5% | — |
Math MiMo-V2.5-Pro leads
MiMo-V2.5-Pro: 38.6 (#84), Step 3: 34.9 (#148)
| Benchmark | MiMo-V2.5-Pro | Step 3 |
|---|---|---|
| LMArena Math | 1480 | 1366 |
| ProofBench | 22% | — |
Knowledge MiMo-V2.5-Pro leads
MiMo-V2.5-Pro: 41.5 (#100), Step 3: 36.2 (#161)
| Benchmark | MiMo-V2.5-Pro | Step 3 |
|---|---|---|
| LMArena Expert | 1501 | 1333 |
Multimodal Not comparable
MiMo-V2.5-Pro: —, Step 3: 34.9 (#81)
| Benchmark | MiMo-V2.5-Pro | Step 3 |
|---|---|---|
| LMArena Vision | — | 1176 |
Multilingual MiMo-V2.5-Pro leads
MiMo-V2.5-Pro: 55.3 (#33), Step 3: 46.5 (#154)
| Benchmark | MiMo-V2.5-Pro | Step 3 |
|---|---|---|
| LMArena Non-English | 1449 | 1327 |
| LMArena Chinese | 1507 | 1396 |
| LMArena German | 1455 | 1371 |
| LMArena Korean | 1436 | 1271 |
| LMArena Russian | 1450 | 1331 |
| LMArena Spanish | 1470 | 1372 |
| LMArena French | 1489 | — |
| LMArena Japanese | 1418 | — |
Instruction Following MiMo-V2.5-Pro leads
MiMo-V2.5-Pro: 77.6 (#21), Step 3: 70.6 (#159)
| Benchmark | MiMo-V2.5-Pro | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1477 | 1332 |
Long Context MiMo-V2.5-Pro leads
MiMo-V2.5-Pro: 45.4 (#38), Step 3: 40.3 (#152)
| Benchmark | MiMo-V2.5-Pro | Step 3 |
|---|---|---|
| LMArena Longer Query | 1482 | 1326 |
Writing & Preference MiMo-V2.5-Pro leads
MiMo-V2.5-Pro: 65.5 (#47), Step 3: 54.5 (#146)
| Benchmark | MiMo-V2.5-Pro | Step 3 |
|---|---|---|
| LMArena Text | 1465 | 1351 |
| LMArena Creative Writing | 1440 | 1322 |
| LMArena Multi-Turn | 1477 | 1340 |
| EQ-Bench Creative Writing | 1493 | — |
| EQ-Bench 4 | 1208 | — |
Frequently asked questions
Is MiMo-V2.5-Pro better than Step 3?
MiMo-V2.5-Pro is the stronger model overall, scoring 44.8 to 39.9 on the Noometry Index.
Is MiMo-V2.5-Pro or Step 3 better for coding?
MiMo-V2.5-Pro scores higher on coding benchmarks: 47.0 versus 39.5 in the Noometry coding category.
How many benchmarks do MiMo-V2.5-Pro and Step 3 share?
15 benchmarks have published results for both models. MiMo-V2.5-Pro has 27 scored results on Noometry and Step 3 has 17.