Step 5 Preview vs Inkling
Step 5 Preview leads Inkling on coding, 61.1 to 31.5 on the Vibe Coding Index, and Step 5 Preview costs 1.5x less per output token ($2.70 vs $4.05 per million). Updated October 22, 2026; 50 benchmarks have a result for both.
Step 5 Preview or Inkling: which to pick
Pick Step 5 Preview for coding: it scores 61.1 on the Vibe Coding Index against 31.5 for Inkling, though on 4 benchmarks against 6.
Pick Inkling for work measured by LMArena Text: math or LMArena Text: mathematical work, where it leads.
- Shared results
- 50
- Step 5 Preview only
- 11
- Inkling only
- 52
- 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
Step 5 Preview
Step 5 Preview scores 61.1 against 31.5.
4 and 6 benchmarks behind the scores
Intelligence
AA Intelligence Index
Step 5 Preview
Step 5 Preview leads, 43.7 against 25.0.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only Inkling has a AA Agentic Index result, 22.5.
Directional only
Reasoning
GPQA Diamond
No call
Only Inkling has a GPQA Diamond result, 87.1%.
Directional only
Knowledge
MMLU Pro
No call
Only Inkling has a MMLU Pro result, 86.3%.
Directional only
Web design
Design Arena: websites
No call
Only Inkling has a Design Arena: websites result, 1224.
Directional only
General
Vals Index
No call
Only Inkling has a Vals Index result, 29.0%.
Directional only
Long documents
Listed context window
Step 5 Preview
Step 5 Preview takes 1.05M tokens against 524K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Step 5 Preview
Step 5 Preview $0.0024, Inkling $0.0030 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only Inkling has the number, $0.76.
Directional only
At a glance
- Coding index
- Step 5 Preview 61.1 from 4 benchmarks, Inkling 31.5 from 6 benchmarks.
- Widest category
- Coding, 23.6 points apart on average over 11 shared benchmarks.
- Widest single gap
- Vibe Code Bench (Vals AI): Step 5 Preview 70.4% against Inkling 19.2%, 51.2 points apart on a 0 to 100 scale.
- Output price
- Step 5 Preview $2.70 against Inkling $4.05 per million output tokens, 1.5x apart.
- Context window
- Step 5 Preview takes 1.05M tokens, Inkling 524K.
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 | Inkling | Ties |
|---|---|---|---|---|
| Coding | 11 | 0 | ||
| Intelligence | 1 | 0 | ||
| Agentic work | 8 | 0 | ||
| Reasoning | 5 | 0 | ||
| Math | 1 | 2 | ||
| Knowledge | 0 | 4 | ||
| Web design | 1 | 0 | ||
| General | 10 | 7 | ||
| All shared boards | 37 | 13 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index110
| Benchmark | Step 5 Preview | Inkling | Leader |
|---|---|---|---|
| LiveBench coding | 85.6% | 64.0% | Step 5 Preview |
| LMArena WebDev | 1567 | 1414 | Step 5 Preview |
| AA Coding Index | Not measured | 52.1 | Only Inkling measured |
| LiveCodeBench (Vals AI) | Not measured | 85.5% | Only Inkling measured |
| SWE-bench Verified (Vals AI) | Not measured | 77.6% | Only Inkling measured |
| Terminal-Bench 4 (Vals AI) | 31.8% | 0.5% | Step 5 Preview |
| Vibe Code Bench (Vals AI) | 70.4% | 19.2% | Step 5 Preview |
| Code migration (Vals AI) | 39.0% | 11.8% | Step 5 Preview |
| ProgramBench (Vals AI) | Not measured | 0.0% | Only Inkling measured |
| IOI (Vals AI) | 38.1% | 14.9% | Step 5 Preview |
| Terminal-Bench 2.1 (Vals AI) | Not measured | 47.6% | Only Inkling measured |
| SWE-bench Multimodal (Vals AI) | 40.8% | Not measured | Only Step 5 Preview measured |
| Vibe Code Bench 1-100 (Vals AI) | Not measured | 7.3% | Only Inkling measured |
| SkillsBench (Vals AI) | Not measured | 26.1% | Only Inkling measured |
| CyberBench (Vals AI) | Not measured | 66.8% | Only Inkling measured |
| SciCode | 58.9% | 47.0% | Step 5 Preview |
| FrontierCode | Not measured | 14.0% | Only Inkling measured |
| FrontierSWE | Not measured | 4.1% | Only Inkling measured |
| WeirdML | Not measured | 32.3% | Only Inkling measured |
| ALE-Bench | Not measured | 946.0 | Only Inkling measured |
| LMArena Text: coding | 1485 | 1466 | Step 5 Preview |
| LMArena Text: software and IT | 1473 | 1465 | Step 5 Preview |
| LMArena WebDev: React | 1583 | 1404 | Step 5 Preview |
| LMArena WebDev: HTML | 1556 | 1399 | Step 5 Preview |
| LMArena WebDev: from an image | 1550 | Not measured | Only Step 5 Preview measured |
| Neither model has a result on the other 14 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Step 5 Preview | Inkling | Leader |
|---|---|---|---|
| AA Intelligence Index | 43.7 | 25.0 | Step 5 Preview |
| Epoch Capabilities Index | Not measured | 148.4 | Only Inkling measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index80
| Benchmark | Step 5 Preview | Inkling | Leader |
|---|---|---|---|
| AA Agentic Index | Not measured | 22.5 | Only Inkling measured |
| Design Arena: agents building web apps | Not measured | 1196 | Only Inkling measured |
| LiveBench research | 72.8% | 59.9% | Step 5 Preview |
| LiveBench browser | 24.0% | 16.0% | Step 5 Preview |
| LiveBench long agentic | 27.5% | 14.1% | Step 5 Preview |
| SREBench (Vals AI) | 0.4% | 0.0% | Step 5 Preview |
| Finance Agent (Vals AI) | 50.7% | 46.6% | Step 5 Preview |
| Tax Agent Bench (Vals AI) | 27.3% | 15.3% | Step 5 Preview |
| Legal Research Bench (Vals AI) | 40.4% | 28.4% | Step 5 Preview |
| Harvey's Legal Agent Benchmark (Vals AI) | Not measured | 3.8% | Only Inkling measured |
| Excel Modeling Benchmark (Vals AI) | 57.1% | 38.4% | Step 5 Preview |
| BioMysteryBench (Vals AI) | 67.4% | Not measured | Only Step 5 Preview measured |
| Terminal-Bench-Science (Vals AI) | 2.9% | Not measured | Only Step 5 Preview measured |
| Vals Science Index | 29.6% | Not measured | Only Step 5 Preview measured |
| APEX-Agents | Not measured | 33.8% | Only Inkling measured |
| Neither model has a result on the other 26 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index50
| Benchmark | Step 5 Preview | Inkling | Leader |
|---|---|---|---|
| GPQA Diamond | Not measured | 87.1% | Only Inkling measured |
| LiveBench reasoning | 83.8% | 78.3% | Step 5 Preview |
| MysteryMechanism (Vals AI) | 18.5% | Not measured | Only Step 5 Preview measured |
| MMMU Pro (Vals AI) | Not measured | 78.5% | Only Inkling measured |
| GPQA Diamond (Artificial Analysis run) | Not measured | 87.2% | Only Inkling measured |
| Humanity's Last Exam (Artificial Analysis run) | 46.5% | 31.9% | Step 5 Preview |
| GPQA Diamond (Epoch AI run) | Not measured | 88.3% | Only Inkling measured |
| ARC-AGI | Not measured | 79.5% | Only Inkling measured |
| ARC-AGI-2 | Not measured | 36.5% | Only Inkling measured |
| SimpleBench | Not measured | 50.0% | Only Inkling measured |
| Chess puzzles | Not measured | 21.0% | Only Inkling measured |
| LMArena Text: hard prompts | 1461 | 1451 | Step 5 Preview |
| LMArena Text: expert | 1485 | 1466 | Step 5 Preview |
| LMArena Text: hard prompts in English | 1454 | 1448 | Step 5 Preview |
| LMArena Vision: diagrams | 1308 | Not measured | Only Step 5 Preview measured |
| LMArena Vision: homework | 1265 | Not measured | Only Step 5 Preview measured |
| Neither model has a result on the other 6 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index12
| Benchmark | Step 5 Preview | Inkling | Leader |
|---|---|---|---|
| OTIS Mock AIME | Not measured | 88.9% | Only Inkling measured |
| FrontierMath, tiers 1 to 3 | Not measured | 33.3% | Only Inkling measured |
| FrontierMath, tier 4 | Not measured | 4.9% | Only Inkling measured |
| ProofBench | 42.0% | 0.0% | Step 5 Preview |
| LMArena Text: math | 1458 | 1479 | Inkling |
| LMArena Text: mathematical work | 1460 | 1460 | Inkling |
| Neither model has a result on the other 7 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index04
| Benchmark | Step 5 Preview | Inkling | Leader |
|---|---|---|---|
| MMLU Pro | Not measured | 86.3% | Only Inkling measured |
| LegalBench (Vals AI) | Not measured | 83.0% | Only Inkling measured |
| CorpFin (Vals AI) | Not measured | 68.6% | Only Inkling measured |
| TaxEval (Vals AI) | Not measured | 75.3% | Only Inkling measured |
| MortgageTax (Vals AI) | Not measured | 64.0% | Only Inkling measured |
| MedCode (Vals AI) | Not measured | 41.2% | Only Inkling measured |
| SimpleQA Verified | Not measured | 40.3% | Only Inkling measured |
| LMArena Text: science | 1454 | 1455 | Inkling |
| LMArena Text: medicine and healthcare | 1439 | 1447 | Inkling |
| LMArena Text: legal and government | 1437 | 1448 | Inkling |
| LMArena Text: business and finance | 1435 | 1438 | Inkling |
| Neither model has a result on the other 7 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Step 5 Preview | Inkling | Leader |
|---|---|---|---|
| Design Arena: websites | Not measured | 1224 | Only Inkling measured |
| Design Arena: UI components | Not measured | 1199 | Only Inkling measured |
| Design Arena: game dev | Not measured | 1165 | Only Inkling measured |
| Design Arena: data viz | Not measured | 1157 | Only Inkling measured |
| Design Arena: 3D | Not measured | 1160 | Only Inkling measured |
| Design Arena: all code categories | Not measured | 1205 | Only Inkling measured |
| Design Arena: SVG | Not measured | 1107 | Only Inkling measured |
| Design Arena: ASCII art | Not measured | 1089 | Only Inkling measured |
| LiveBench design | 76.9% | 58.3% | Step 5 Preview |
GeneralLike-for-likePublic boards, shown as published, kept out of the index107
| Benchmark | Step 5 Preview | Inkling | Leader |
|---|---|---|---|
| Vals Index | Not measured | 29.0% | Only Inkling measured |
| LiveBench data analysis | 63.5% | 72.8% | Inkling |
| Public Benefits Bench (Vals AI) | 58.1% | 58.5% | Inkling |
| SAGE (Vals AI) | Not measured | 36.5% | Only Inkling measured |
| MedScribe (Vals AI) | Not measured | 85.4% | Only Inkling measured |
| Vals Multimodal Index | Not measured | 49.4% | Only Inkling measured |
| Long context reasoning (AA-LCR) | 88.3% | 77.3% | Step 5 Preview |
| DTBench | Not measured | 87.5% | Only Inkling measured |
| LMCA | Not measured | 37.6% | Only Inkling measured |
| LMArena Text | 1440 | 1442 | Inkling |
| LMArena Text: instruction following | 1438 | 1425 | Step 5 Preview |
| LMArena Text: creative writing | 1409 | 1390 | Step 5 Preview |
| LMArena Vision | 1265 | Not measured | Only Step 5 Preview measured |
| LMArena Text: English | 1447 | 1442 | Step 5 Preview |
| LMArena Text: non-English | 1428 | 1434 | Inkling |
| LMArena Text: Chinese | 1500 | 1493 | Step 5 Preview |
| LMArena Text: German | Not measured | 1445 | Only Inkling measured |
| LMArena Text: Japanese | 1383 | 1429 | Inkling |
| LMArena Text: Korean | Not measured | 1403 | Only Inkling measured |
| LMArena Text: French | 1438 | 1455 | Inkling |
| LMArena Text: Spanish | 1441 | 1449 | Inkling |
| LMArena Text: Russian | 1433 | 1430 | Step 5 Preview |
| LMArena Text: Polish | Not measured | 1450 | Only Inkling measured |
| LMArena Text: multi-turn | 1437 | 1437 | Step 5 Preview |
| LMArena Text: longer queries | 1449 | 1435 | Step 5 Preview |
| LMArena Text: writing and language | 1425 | 1404 | Step 5 Preview |
| LMArena Text: entertainment and media | 1412 | 1394 | Step 5 Preview |
| LMArena Vision: English | 1290 | Not measured | Only Step 5 Preview measured |
| LMArena Vision: reading text | 1282 | Not measured | Only Step 5 Preview measured |
| Neither model has a result on the other 17 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Step 5 Preview | Inkling | 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
Step 5 Preview costs less
Repository review
50K input + 3K output tokens
Step 5 Preview costs less
Agent loop
200K input + 10K output tokens
Step 5 Preview 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 | Thinking Machines Inkling |
|---|---|---|
| Maker | StepFun | Thinking Machines |
| Weights | Open weights | Open weights |
| Released | October 8, 2026 | July 17, 2026 |
| Context window | 1.05M | 524K |
| Input $/Mtok | $1.00 | $1.00 |
| Output $/Mtok | $2.70 | $4.05 |
| Coding index | 61.1 | 31.5 |
| Independent measurements behind it | 4 | 6 |
| Cost per solved task | Not computable | $0.76 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Step 5 Preview better than Inkling for coding?
Pick Step 5 Preview for coding: it scores 61.1 on the Vibe Coding Index against 31.5 for Inkling, though on 4 benchmarks against 6. Pick Inkling for work measured by LMArena Text: math or LMArena Text: mathematical work, where it leads.
Which is cheaper, Step 5 Preview or Inkling?
Step 5 Preview costs $1.00 per million input tokens and $2.70 per million output tokens; Inkling costs $1.00 and $4.05. Cost per solved task is known for Inkling only.
Which has the bigger context window, Step 5 Preview or Inkling?
Step 5 Preview, with 1.05M tokens against 524K.
How many benchmarks is the Step 5 Preview vs Inkling comparison based on?
50 benchmarks have a result for both models as of October 22, 2026. Step 5 Preview's coding index rests on 4 independent benchmarks and Inkling's on 6. Where only one model has a result, the page says so instead of naming a winner.