Model comparison
Inkling-Small vs Step 3.5 Flash
Inkling-Small is the stronger model overall, scoring 46.5 to 42.3 on the Noometry Index. Step 3.5 Flash costs 4.2× less per token, which makes it the better buy when Inkling-Small's lead doesn't matter for your workload.
Last verified . 17 shared benchmarks.
StepFunSummary
- They share 17 benchmarks with published results for both. Inkling-Small scores higher in 7 categories and Step 3.5 Flash in 1 category; 5 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Inkling-Small leads 38.6 to 22.2.
- Step 3.5 Flash is cheaper at $0.10 / $0.30 per million input/output tokens, against $0.45 / $1.20 for Inkling-Small.
- Inkling-Small accepts more context: 524K tokens versus 256K.
Side by side
| Inkling-Small | Step 3.5 Flash | |
|---|---|---|
| Provider | Thinking Machines Lab | StepFun |
| Noometry Index | 46.5 | 42.3 |
| Released | 2026-07-15 | 2026-01-29 |
| Weights | Open | Open |
| Context window | 524K | 256K |
| Max output | 1.05M | 256K |
| Input $ / M tokens | $0.45 | $0.10 |
| Output $ / M tokens | $1.20 | $0.30 |
| Results tracked | 33 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Inkling-Small leads
Inkling-Small: 43.6 (#85), Step 3.5 Flash: 42.4 (#105)
| Benchmark | Inkling-Small | Step 3.5 Flash |
|---|---|---|
| LMArena Coding | 1451 | 1436 |
| LMArena WebDev | 1409 | — |
| SciCode | 48.7% | — |
Reasoning Inkling-Small leads
Inkling-Small: 38.6 (#63), Step 3.5 Flash: 22.2 (#202)
| Benchmark | Inkling-Small | Step 3.5 Flash |
|---|---|---|
| LMArena Hard Prompts | 1423 | 1411 |
| ARC-AGI-2 | 40.1% | — |
| NYT Connections (extended) | — | 28.4% |
| ARC-AGI-1 | 84% | — |
| CritPt | 8.3% | — |
| Chess Puzzles | 18% | — |
| Mystery Game Puzzles | 6% | — |
| Epoch Capabilities Index | 150.15 | — |
Math Inkling-Small leads
Inkling-Small: 45.1 (#77), Step 3.5 Flash: 42.6 (#84)
| Benchmark | Inkling-Small | Step 3.5 Flash |
|---|---|---|
| LMArena Math | 1459 | 1408 |
| FrontierMath (Tiers 1-3) | 46.3% | — |
| FrontierMath Tier 4 | 17.1% | — |
| MathArena Final-Answer Competitions | — | 66.8% |
| OTIS Mock AIME 2024-2025 | 90% | — |
| ProofBench | 6% | — |
Knowledge Inkling-Small leads
Inkling-Small: 48.2 (#77), Step 3.5 Flash: 39.6 (#132)
| Benchmark | Inkling-Small | Step 3.5 Flash |
|---|---|---|
| LMArena Expert | 1442 | 1421 |
| GPQA Diamond | 88.5% | — |
| SimpleQA Verified | 19.1% | — |
Multimodal Not comparable
Inkling-Small: 39.1 (#62), Step 3.5 Flash: —
| Benchmark | Inkling-Small | Step 3.5 Flash |
|---|---|---|
| LMArena Vision | 1235 | — |
Multilingual Inkling-Small leads
Inkling-Small: 51.7 (#104), Step 3.5 Flash: 50.5 (#119)
| Benchmark | Inkling-Small | Step 3.5 Flash |
|---|---|---|
| LMArena Non-English | 1402 | 1385 |
| LMArena Chinese | 1465 | 1447 |
| LMArena French | 1436 | 1421 |
| LMArena German | 1405 | 1405 |
| LMArena Japanese | 1405 | 1354 |
| LMArena Korean | 1363 | 1352 |
| LMArena Russian | 1391 | 1385 |
| LMArena Spanish | 1428 | 1419 |
Instruction Following Too close to call
Inkling-Small: 73.8 (#114), Step 3.5 Flash: 73.1 (#124)
| Benchmark | Inkling-Small | Step 3.5 Flash |
|---|---|---|
| LMArena Instruction Following | 1399 | 1385 |
Long Context Too close to call
Inkling-Small: 42.7 (#118), Step 3.5 Flash: 42.8 (#117)
| Benchmark | Inkling-Small | Step 3.5 Flash |
|---|---|---|
| LMArena Longer Query | 1401 | 1402 |
Writing & Preference Too close to call
Inkling-Small: 59.6 (#107), Step 3.5 Flash: 58.8 (#113)
| Benchmark | Inkling-Small | Step 3.5 Flash |
|---|---|---|
| LMArena Text | 1414 | 1403 |
| LMArena Creative Writing | 1331 | 1357 |
| LMArena Multi-Turn | 1418 | 1405 |
| EQ-Bench Creative Writing | 1491 | — |
Frequently asked questions
Is Inkling-Small better than Step 3.5 Flash?
Inkling-Small is the stronger model overall, scoring 46.5 to 42.3 on the Noometry Index. Step 3.5 Flash costs 4.2× less per token, which makes it the better buy when Inkling-Small's lead doesn't matter for your workload.
Which is cheaper, Inkling-Small or Step 3.5 Flash?
Step 3.5 Flash is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; Inkling-Small lists at $0.45 and $1.20.
Is Inkling-Small or Step 3.5 Flash better for coding?
Inkling-Small scores higher on coding benchmarks: 43.6 versus 42.4 in the Noometry coding category.
Which has the bigger context window?
Inkling-Small does, with 524K tokens against 256K.
How many benchmarks do Inkling-Small and Step 3.5 Flash share?
17 benchmarks have published results for both models. Inkling-Small has 33 scored results on Noometry and Step 3.5 Flash has 19.