Step 5 Preview vs MiMo-V2.6-Pro
MiMo-V2.6-Pro leads Step 5 Preview on coding, 65.4 to 61.1 on the Vibe Coding Index, and MiMo-V2.6-Pro costs 3.1x less per output token ($0.87 vs $2.70 per million). Updated October 22, 2026; 56 benchmarks have a result for both.
Step 5 Preview or MiMo-V2.6-Pro: which to pick
Pick MiMo-V2.6-Pro for coding: it scores 65.4 on the Vibe Coding Index against 61.1 for Step 5 Preview.
Pick Step 5 Preview for work measured by LiveBench coding or Terminal-Bench 4 (Vals AI), where it leads.
- Shared results
- 56
- Step 5 Preview only
- 5
- MiMo-V2.6-Pro only
- 17
- Like-for-like categories
- 8 of 9
Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.
Which one for your work
Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.
Coding
Vibe Coding Index, six public coding benchmarks
MiMo-V2.6-Pro
MiMo-V2.6-Pro scores 65.4 against 61.1.
4 benchmarks behind each score
Intelligence
AA Intelligence Index
MiMo-V2.6-Pro
MiMo-V2.6-Pro leads, 46.3 against 43.7.
Same board, both measured
Web design
Design Arena: websites
No call
Only MiMo-V2.6-Pro has a Design Arena: websites result, 1307.
Directional only
General
Vals Index
No call
Only MiMo-V2.6-Pro has a Vals Index result, 57.8%.
Directional only
Long documents
Listed context window
MiMo-V2.6-Pro
MiMo-V2.6-Pro takes 1.05M tokens against 1.05M.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
MiMo-V2.6-Pro
Step 5 Preview $0.0024, MiMo-V2.6-Pro $0.0009 per turn.
List prices
At a glance
- Coding index
- Step 5 Preview 61.1 from 4 benchmarks, MiMo-V2.6-Pro 65.4 from 4 benchmarks.
- Widest category
- Math, 14.6 points apart on average over 3 shared benchmarks.
- Widest single gap
- LiveBench browser: Step 5 Preview 24.0% against MiMo-V2.6-Pro 88.0%, 64.0 points apart on a 0 to 100 scale.
- Output price
- Step 5 Preview $2.70 against MiMo-V2.6-Pro $0.87 per million output tokens, 3.1x apart.
- Context window
- Step 5 Preview takes 1.05M tokens, MiMo-V2.6-Pro 1.05M.
Benchmark by benchmark
First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.
| Category | Step 5 Preview | Bars | MiMo-V2.6-Pro | Ties |
|---|---|---|---|---|
| Coding | 2 | 11 | ||
| Intelligence | 0 | 1 | ||
| Agentic work | 0 | 8 | 1 tie | |
| Reasoning | 4 | 4 | ||
| Math | 0 | 3 | ||
| Knowledge | 0 | 4 | ||
| Web design | 0 | 1 | ||
| General | 4 | 13 | ||
| All shared boards | 10 | 45 | 1 tie |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index211
| Benchmark | Step 5 Preview | MiMo-V2.6-Pro | Leader |
|---|---|---|---|
| LiveBench coding | 85.6% | 81.5% | Step 5 Preview |
| LMArena WebDev | 1567 | 1625 | MiMo-V2.6-Pro |
| Terminal-Bench 4 (Vals AI) | 31.8% | 31.3% | Step 5 Preview |
| Vibe Code Bench (Vals AI) | 70.4% | 85.2% | MiMo-V2.6-Pro |
| Code migration (Vals AI) | 39.0% | 43.0% | MiMo-V2.6-Pro |
| ProgramBench (Vals AI) | Not measured | 0.5% | Only MiMo-V2.6-Pro measured |
| IOI (Vals AI) | 38.1% | 39.3% | MiMo-V2.6-Pro |
| Terminal-Bench 2.1 (Vals AI) | Not measured | 67.8% | Only MiMo-V2.6-Pro measured |
| SWE-bench Multimodal (Vals AI) | 40.8% | 41.3% | MiMo-V2.6-Pro |
| CyberBench (Vals AI) | Not measured | 72.9% | Only MiMo-V2.6-Pro measured |
| SciCode | 58.9% | 60.9% | MiMo-V2.6-Pro |
| ALE-Bench | Not measured | 1158.1 | Only MiMo-V2.6-Pro measured |
| LMArena Text: coding | 1485 | 1533 | MiMo-V2.6-Pro |
| LMArena Text: software and IT | 1473 | 1528 | MiMo-V2.6-Pro |
| LMArena WebDev: React | 1583 | 1639 | MiMo-V2.6-Pro |
| LMArena WebDev: HTML | 1556 | 1616 | MiMo-V2.6-Pro |
| LMArena WebDev: from an image | 1550 | 1598 | MiMo-V2.6-Pro |
| Neither model has a result on the other 22 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Step 5 Preview | MiMo-V2.6-Pro | Leader |
|---|---|---|---|
| AA Intelligence Index | 43.7 | 46.3 | MiMo-V2.6-Pro |
| Neither model has a result on the other 1 board here | |||
Agentic workLike-for-likePublic boards, shown as published, kept out of the index08
| Benchmark | Step 5 Preview | MiMo-V2.6-Pro | Leader |
|---|---|---|---|
| Design Arena: agents building web apps | Not measured | 1290 | Only MiMo-V2.6-Pro measured |
| LiveBench research | 72.8% | 76.7% | MiMo-V2.6-Pro |
| LiveBench browser | 24.0% | 88.0% | MiMo-V2.6-Pro |
| LiveBench long agentic | 27.5% | 47.5% | MiMo-V2.6-Pro |
| SREBench (Vals AI) | 0.4% | 3.0% | MiMo-V2.6-Pro |
| Finance Agent (Vals AI) | 50.7% | 57.3% | MiMo-V2.6-Pro |
| Tax Agent Bench (Vals AI) | 27.3% | 32.4% | MiMo-V2.6-Pro |
| Legal Research Bench (Vals AI) | 40.4% | 47.1% | MiMo-V2.6-Pro |
| Harvey's Legal Agent Benchmark (Vals AI) | Not measured | 13.8% | Only MiMo-V2.6-Pro measured |
| Excel Modeling Benchmark (Vals AI) | 57.1% | 62.9% | MiMo-V2.6-Pro |
| BioMysteryBench (Vals AI) | 67.4% | Not measured | Only Step 5 Preview measured |
| Terminal-Bench-Science (Vals AI) | 2.9% | 2.9% | Tie |
| Vals Science Index | 29.6% | Not measured | Only Step 5 Preview measured |
| APEX-Agents | Not measured | 54.4% | Only MiMo-V2.6-Pro measured |
| Neither model has a result on the other 27 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index44
| Benchmark | Step 5 Preview | MiMo-V2.6-Pro | Leader |
|---|---|---|---|
| LiveBench reasoning | 83.8% | 79.6% | Step 5 Preview |
| MysteryMechanism (Vals AI) | 18.5% | 15.3% | Step 5 Preview |
| Humanity's Last Exam (Artificial Analysis run) | 46.5% | 49.4% | MiMo-V2.6-Pro |
| LMArena Text: hard prompts | 1461 | 1511 | MiMo-V2.6-Pro |
| LMArena Text: expert | 1485 | 1541 | MiMo-V2.6-Pro |
| LMArena Text: hard prompts in English | 1454 | 1520 | MiMo-V2.6-Pro |
| LMArena Vision: diagrams | 1308 | 1281 | Step 5 Preview |
| LMArena Vision: homework | 1265 | 1264 | Step 5 Preview |
| Neither model has a result on the other 14 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index03
| Benchmark | Step 5 Preview | MiMo-V2.6-Pro | Leader |
|---|---|---|---|
| ProofBench | 42.0% | 70.0% | MiMo-V2.6-Pro |
| LMArena Text: math | 1458 | 1500 | MiMo-V2.6-Pro |
| LMArena Text: mathematical work | 1460 | 1511 | MiMo-V2.6-Pro |
| Neither model has a result on the other 10 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index04
| Benchmark | Step 5 Preview | MiMo-V2.6-Pro | Leader |
|---|---|---|---|
| MedCode (Vals AI) | Not measured | 45.0% | Only MiMo-V2.6-Pro measured |
| LMArena Text: science | 1454 | 1506 | MiMo-V2.6-Pro |
| LMArena Text: medicine and healthcare | 1439 | 1497 | MiMo-V2.6-Pro |
| LMArena Text: legal and government | 1437 | 1485 | MiMo-V2.6-Pro |
| LMArena Text: business and finance | 1435 | 1468 | MiMo-V2.6-Pro |
| Neither model has a result on the other 13 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Step 5 Preview | MiMo-V2.6-Pro | Leader |
|---|---|---|---|
| Design Arena: websites | Not measured | 1307 | Only MiMo-V2.6-Pro measured |
| Design Arena: UI components | Not measured | 1337 | Only MiMo-V2.6-Pro measured |
| Design Arena: game dev | Not measured | 1313 | Only MiMo-V2.6-Pro measured |
| Design Arena: data viz | Not measured | 1337 | Only MiMo-V2.6-Pro measured |
| Design Arena: 3D | Not measured | 1329 | Only MiMo-V2.6-Pro measured |
| Design Arena: all code categories | Not measured | 1316 | Only MiMo-V2.6-Pro measured |
| LiveBench design | 76.9% | 78.5% | MiMo-V2.6-Pro |
| Neither model has a result on the other 2 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index413
| Benchmark | Step 5 Preview | MiMo-V2.6-Pro | Leader |
|---|---|---|---|
| Vals Index | Not measured | 57.8% | Only MiMo-V2.6-Pro measured |
| LiveBench data analysis | 63.5% | 72.3% | MiMo-V2.6-Pro |
| Public Benefits Bench (Vals AI) | 58.1% | 68.9% | MiMo-V2.6-Pro |
| SAGE (Vals AI) | Not measured | 45.0% | Only MiMo-V2.6-Pro measured |
| MedScribe (Vals AI) | Not measured | 88.3% | Only MiMo-V2.6-Pro measured |
| Long context reasoning (AA-LCR) | 88.3% | 86.3% | Step 5 Preview |
| LMArena Text | 1440 | 1491 | MiMo-V2.6-Pro |
| LMArena Text: instruction following | 1438 | 1491 | MiMo-V2.6-Pro |
| LMArena Text: creative writing | 1409 | 1466 | MiMo-V2.6-Pro |
| LMArena Vision | 1265 | 1263 | Step 5 Preview |
| LMArena Text: English | 1447 | 1504 | MiMo-V2.6-Pro |
| LMArena Text: non-English | 1428 | 1474 | MiMo-V2.6-Pro |
| LMArena Text: Chinese | 1500 | 1529 | MiMo-V2.6-Pro |
| LMArena Text: Japanese | 1383 | Not measured | Only Step 5 Preview measured |
| LMArena Text: French | 1438 | Not measured | Only Step 5 Preview measured |
| LMArena Text: Spanish | 1441 | Not measured | Only Step 5 Preview measured |
| LMArena Text: Russian | 1433 | 1479 | MiMo-V2.6-Pro |
| LMArena Text: multi-turn | 1437 | 1466 | MiMo-V2.6-Pro |
| LMArena Text: longer queries | 1449 | 1501 | MiMo-V2.6-Pro |
| LMArena Text: writing and language | 1425 | 1470 | MiMo-V2.6-Pro |
| LMArena Text: entertainment and media | 1412 | 1465 | MiMo-V2.6-Pro |
| LMArena Vision: English | 1290 | 1268 | Step 5 Preview |
| LMArena Vision: reading text | 1282 | 1270 | Step 5 Preview |
| Neither model has a result on the other 23 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Step 5 Preview | MiMo-V2.6-Pro | Leader |
|---|---|---|---|
| Neither model has a result on 5 boards here | |||
What each workload costs
Three fixed token mixes at each model's listed price, so per-token rates become a bill.
Chat turn
1K input + 500 output tokens
MiMo-V2.6-Pro costs less
Repository review
50K input + 3K output tokens
MiMo-V2.6-Pro costs less
Agent loop
200K input + 10K output tokens
MiMo-V2.6-Pro costs less
Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.
Specification differences
The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.
| Specification | StepFun Step 5 Preview | Xiaomi MiMo-V2.6-Pro |
|---|---|---|
| Maker | StepFun | Xiaomi |
| Weights | Open weights | Open weights |
| Released | October 8, 2026 | September 21, 2026 |
| Context window | 1.05M | 1.05M |
| Input $/Mtok | $1.00 | $0.435 |
| Output $/Mtok | $2.70 | $0.87 |
| Coding index | 61.1 | 65.4 |
| Independent measurements behind it | 4 | 4 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Step 5 Preview better than MiMo-V2.6-Pro for coding?
Pick MiMo-V2.6-Pro for coding: it scores 65.4 on the Vibe Coding Index against 61.1 for Step 5 Preview. Pick Step 5 Preview for work measured by LiveBench coding or Terminal-Bench 4 (Vals AI), where it leads.
Which is cheaper, Step 5 Preview or MiMo-V2.6-Pro?
Step 5 Preview costs $1.00 per million input tokens and $2.70 per million output tokens; MiMo-V2.6-Pro costs $0.435 and $0.87. Cost per solved task is known for neither of them.
Which has the bigger context window, Step 5 Preview or MiMo-V2.6-Pro?
MiMo-V2.6-Pro, with 1.05M tokens against 1.05M.
How many benchmarks is the Step 5 Preview vs MiMo-V2.6-Pro comparison based on?
56 benchmarks have a result for both models as of October 22, 2026. Step 5 Preview's coding index rests on 4 independent benchmarks and MiMo-V2.6-Pro's on 4. Where only one model has a result, the page says so instead of naming a winner.