Model comparison
MiniMax-M2.5 vs Step 5 Preview
Step 5 Preview is the stronger model overall, scoring 47.9 to 38.3 on the Noometry Index. MiniMax-M2.5 costs 2.7× less per token, which makes it the better buy when Step 5 Preview's lead doesn't matter for your workload.
Last verified . 15 shared benchmarks.
MiniMax
StepFunSummary
- They share 15 benchmarks with published results for both. MiniMax-M2.5 scores higher in 0 categories and Step 5 Preview in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Step 5 Preview leads 40.0 to 17.5.
- The biggest single-benchmark swing is ProofBench: 4% for MiniMax-M2.5 and 42% for Step 5 Preview.
- MiniMax-M2.5 is cheaper at $0.30 / $1.20 per million input/output tokens, against $1 / $2.70 for Step 5 Preview.
- Step 5 Preview accepts more context: 1.02M tokens versus 205K.
- MiniMax-M2.5 has downloadable open weights; the other is API-only.
Side by side
| MiniMax-M2.5 | Step 5 Preview | |
|---|---|---|
| Provider | MiniMax | StepFun |
| Noometry Index | 38.3 | 47.9 |
| Released | 2026-02-12 | 2026-09-16 |
| Weights | Open | Proprietary |
| Context window | 205K | 1.02M |
| Max output | 131K | 66K |
| Input $ / M tokens | $0.30 | $1 |
| Output $ / M tokens | $1.20 | $2.70 |
| Results tracked | 33 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 5 Preview leads
MiniMax-M2.5: 48.1 (#58), Step 5 Preview: 51.8 (#36)
| Benchmark | MiniMax-M2.5 | Step 5 Preview |
|---|---|---|
| LMArena WebDev | 1387 | 1564 |
| LMArena Coding | 1381 | 1480 |
| SWE-bench Verified (bash only) | 75.8% | — |
| SWE-bench Multilingual | 68.3% | — |
| SciCode | — | 58.9% |
| ALE-Bench | 618.17 | — |
Agentic & Tool Use Not comparable
MiniMax-M2.5: 30.4 (#77), Step 5 Preview: —
| Benchmark | MiniMax-M2.5 | Step 5 Preview |
|---|---|---|
| Terminal-Bench | 42.7% | — |
| Vending-Bench 2 | -23.16 | — |
Reasoning Step 5 Preview leads
MiniMax-M2.5: 17.5 (#292), Step 5 Preview: 40.0 (#57)
| Benchmark | MiniMax-M2.5 | Step 5 Preview |
|---|---|---|
| LMArena Hard Prompts | 1372 | 1465 |
| ARC-AGI-2 | 4.9% | — |
| Kagi LLM Benchmark | 55.2% | — |
| NYT Connections (extended) | 16.8% | — |
| ARC-AGI-1 | 63.7% | — |
| CritPt | — | 20.9% |
| Epoch Capabilities Index | 146.68 | — |
Math Step 5 Preview leads
MiniMax-M2.5: 26.9 (#253), Step 5 Preview: 46.1 (#72)
| Benchmark | MiniMax-M2.5 | Step 5 Preview |
|---|---|---|
| ProofBench | 4% | 42% |
| LMArena Math | 1378 | 1470 |
Knowledge Step 5 Preview leads
MiniMax-M2.5: 39.2 (#135), Step 5 Preview: 41.2 (#112)
| Benchmark | MiniMax-M2.5 | Step 5 Preview |
|---|---|---|
| LMArena Expert | 1379 | 1470 |
| Vectara Hallucination Rate | 9.1% | — |
Multimodal Not comparable
MiniMax-M2.5: —, Step 5 Preview: 41.0 (#41)
| Benchmark | MiniMax-M2.5 | Step 5 Preview |
|---|---|---|
| LMArena Vision | — | 1267 |
Multilingual Step 5 Preview leads
MiniMax-M2.5: 47.1 (#152), Step 5 Preview: 53.8 (#54)
| Benchmark | MiniMax-M2.5 | Step 5 Preview |
|---|---|---|
| LMArena Non-English | 1338 | 1432 |
| LMArena Chinese | 1393 | 1519 |
| LMArena Russian | 1358 | 1436 |
| LMArena Spanish | 1354 | 1439 |
| LMArena French | 1362 | — |
| LMArena German | 1362 | — |
| LMArena Japanese | 1171 | — |
| LMArena Korean | 1232 | — |
Instruction Following Step 5 Preview leads
MiniMax-M2.5: 71.5 (#148), Step 5 Preview: 76.0 (#50)
| Benchmark | MiniMax-M2.5 | Step 5 Preview |
|---|---|---|
| LMArena Instruction Following | 1353 | 1444 |
Long Context Step 5 Preview leads
MiniMax-M2.5: 37.5 (#216), Step 5 Preview: 44.5 (#64)
| Benchmark | MiniMax-M2.5 | Step 5 Preview |
|---|---|---|
| LMArena Longer Query | 1366 | 1455 |
| CL-bench | 11.4% | — |
| CL-bench Life | 6.3% | — |
Writing & Preference Step 5 Preview leads
MiniMax-M2.5: 53.9 (#153), Step 5 Preview: 62.8 (#71)
| Benchmark | MiniMax-M2.5 | Step 5 Preview |
|---|---|---|
| LMArena Text | 1359 | 1442 |
| LMArena Creative Writing | 1331 | 1410 |
| LMArena Multi-Turn | 1364 | 1447 |
| EQ-Bench Creative Writing | 1361 | — |
Frequently asked questions
Is MiniMax-M2.5 better than Step 5 Preview?
Step 5 Preview is the stronger model overall, scoring 47.9 to 38.3 on the Noometry Index. MiniMax-M2.5 costs 2.7× less per token, which makes it the better buy when Step 5 Preview's lead doesn't matter for your workload.
Which is cheaper, MiniMax-M2.5 or Step 5 Preview?
MiniMax-M2.5 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Step 5 Preview lists at $1 and $2.70.
Is MiniMax-M2.5 or Step 5 Preview better for coding?
Step 5 Preview scores higher on coding benchmarks: 51.8 versus 48.1 in the Noometry coding category.
Which has the bigger context window?
Step 5 Preview does, with 1.02M tokens against 205K.
How many benchmarks do MiniMax-M2.5 and Step 5 Preview share?
15 benchmarks have published results for both models. MiniMax-M2.5 has 33 scored results on Noometry and Step 5 Preview has 18.