Model comparison
Inkling-Small vs Step 5 Preview
Step 5 Preview is the stronger model overall, scoring 47.9 to 46.5 on the Noometry Index. Inkling-Small costs 2.2× less per token, which makes it the better buy when Step 5 Preview's lead doesn't matter for your workload.
Last verified . 18 shared benchmarks.
StepFunSummary
- They share 18 benchmarks with published results for both. Inkling-Small scores higher in 1 category and Step 5 Preview in 8 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in coding, where Step 5 Preview leads 51.8 to 43.6.
- The biggest single-benchmark swing is ProofBench: 6% for Inkling-Small and 42% for Step 5 Preview.
- Inkling-Small is cheaper at $0.45 / $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 524K.
- Inkling-Small has downloadable open weights; the other is API-only.
Side by side
| Inkling-Small | Step 5 Preview | |
|---|---|---|
| Provider | Thinking Machines Lab | StepFun |
| Noometry Index | 46.5 | 47.9 |
| Released | 2026-07-15 | 2026-09-16 |
| Weights | Open | Proprietary |
| Context window | 524K | 1.02M |
| Max output | 1.05M | 66K |
| Input $ / M tokens | $0.45 | $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
Inkling-Small: 43.6 (#85), Step 5 Preview: 51.8 (#36)
| Benchmark | Inkling-Small | Step 5 Preview |
|---|---|---|
| LMArena WebDev | 1409 | 1564 |
| SciCode | 48.7% | 58.9% |
| LMArena Coding | 1451 | 1480 |
Reasoning Step 5 Preview leads
Inkling-Small: 38.6 (#63), Step 5 Preview: 40.0 (#57)
| Benchmark | Inkling-Small | Step 5 Preview |
|---|---|---|
| CritPt | 8.3% | 20.9% |
| LMArena Hard Prompts | 1423 | 1465 |
| ARC-AGI-2 | 40.1% | — |
| ARC-AGI-1 | 84% | — |
| Chess Puzzles | 18% | — |
| Mystery Game Puzzles | 6% | — |
| Epoch Capabilities Index | 150.15 | — |
Math Step 5 Preview leads
Inkling-Small: 45.1 (#77), Step 5 Preview: 46.1 (#72)
| Benchmark | Inkling-Small | Step 5 Preview |
|---|---|---|
| ProofBench | 6% | 42% |
| LMArena Math | 1459 | 1470 |
| FrontierMath (Tiers 1-3) | 46.3% | — |
| FrontierMath Tier 4 | 17.1% | — |
| OTIS Mock AIME 2024-2025 | 90% | — |
Knowledge Inkling-Small leads
Inkling-Small: 48.2 (#77), Step 5 Preview: 41.2 (#112)
| Benchmark | Inkling-Small | Step 5 Preview |
|---|---|---|
| LMArena Expert | 1442 | 1470 |
| GPQA Diamond | 88.5% | — |
| SimpleQA Verified | 19.1% | — |
Multimodal Step 5 Preview leads
Inkling-Small: 39.1 (#62), Step 5 Preview: 41.0 (#41)
| Benchmark | Inkling-Small | Step 5 Preview |
|---|---|---|
| LMArena Vision | 1235 | 1267 |
Multilingual Step 5 Preview leads
Inkling-Small: 51.7 (#104), Step 5 Preview: 53.8 (#54)
| Benchmark | Inkling-Small | Step 5 Preview |
|---|---|---|
| LMArena Non-English | 1402 | 1432 |
| LMArena Chinese | 1465 | 1519 |
| LMArena Russian | 1391 | 1436 |
| LMArena Spanish | 1428 | 1439 |
| LMArena French | 1436 | — |
| LMArena German | 1405 | — |
| LMArena Japanese | 1405 | — |
| LMArena Korean | 1363 | — |
Instruction Following Step 5 Preview leads
Inkling-Small: 73.8 (#114), Step 5 Preview: 76.0 (#50)
| Benchmark | Inkling-Small | Step 5 Preview |
|---|---|---|
| LMArena Instruction Following | 1399 | 1444 |
Long Context Step 5 Preview leads
Inkling-Small: 42.7 (#118), Step 5 Preview: 44.5 (#64)
| Benchmark | Inkling-Small | Step 5 Preview |
|---|---|---|
| LMArena Longer Query | 1401 | 1455 |
Writing & Preference Step 5 Preview leads
Inkling-Small: 59.6 (#107), Step 5 Preview: 62.8 (#71)
| Benchmark | Inkling-Small | Step 5 Preview |
|---|---|---|
| LMArena Text | 1414 | 1442 |
| LMArena Creative Writing | 1331 | 1410 |
| LMArena Multi-Turn | 1418 | 1447 |
| EQ-Bench Creative Writing | 1491 | — |
Frequently asked questions
Is Inkling-Small better than Step 5 Preview?
Step 5 Preview is the stronger model overall, scoring 47.9 to 46.5 on the Noometry Index. Inkling-Small costs 2.2× less per token, which makes it the better buy when Step 5 Preview's lead doesn't matter for your workload.
Which is cheaper, Inkling-Small or Step 5 Preview?
Inkling-Small is cheaper. It lists at $0.45 per million input tokens and $1.20 per million output tokens; Step 5 Preview lists at $1 and $2.70.
Is Inkling-Small or Step 5 Preview better for coding?
Step 5 Preview scores higher on coding benchmarks: 51.8 versus 43.6 in the Noometry coding category.
Which has the bigger context window?
Step 5 Preview does, with 1.02M tokens against 524K.
How many benchmarks do Inkling-Small and Step 5 Preview share?
18 benchmarks have published results for both models. Inkling-Small has 33 scored results on Noometry and Step 5 Preview has 18.