Granite-4.0-H-Small vs Step 3.5 Flash vs Apertus 8B
Too close to call on our weighted score (Granite-4.0-H-Small 63, Step 3.5 Flash 62, Apertus 8B 56). The right pick depends on what you value most.
IBMGranite-4.0-H-Small
63/100- ECI—
- Price$0.064 / $0.265
- Context131K
StepFunStep 3.5 Flash
62/100- ECI—
- Price$0.10 / $0.30
- Context256K
Swiss AI
Apertus 8B
56/100- ECI—
- Price$0.10 / $0.20
- Context66K
Too close to call
It is close. Our weighted score puts them within a point (Granite-4.0-H-Small 63/100, Step 3.5 Flash 62/100, Apertus 8B 56/100), so choose by what matters most for your work: Granite-4.0-H-Small on price and Step 3.5 Flash for long inputs. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
- CapabilityNot enough dataNo independent benchmark covers every model here yet
- Lowest priceGranite-4.0-H-SmallGranite-4.0-H-Small $0.114 · Apertus 8B $0.125 · Step 3.5 Flash $0.15 per 1M tokens (3:1 blend)
- Longest contextStep 3.5 FlashStep 3.5 Flash 256,000 · Granite-4.0-H-Small 131,072 · Apertus 8B 65,536 tokens
- Widest inputsSame inputsGranite-4.0-H-Small: Text · Step 3.5 Flash: Text · Apertus 8B: Text
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | Granite-4.0-H-Small | Step 3.5 Flash | Apertus 8B |
|---|---|---|---|---|
| Price | 50% | 95 | 89 | 93 |
| Inputs & features | 30% | 35 | 35 | 25 |
| Context window | 20% | 24 | 36 | 12 |
| Overall | 100% | 63/100 | 62/100 | 56/100 |
Left out because at least one model lacks the data: capability. The remaining weights were rescaled.
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | Granite-4.0-H-SmallIBM | Step 3.5 FlashStepFun | Apertus 8BSwiss AI |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.064 (best) | $0.10 | $0.10 |
| Output | $0.265 | $0.30 | $0.20 (best) |
| Cached input | — | $0.02 | — |
| Blended (3:1) | $0.114 (best) | $0.15 | $0.125 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official watsonx.ai API | Official StepFun (Global) API | Median of 1 providers |
| Limits | |||
| Context window | 131,072 tokens | 256,000 tokens (best) | 65,536 tokens |
| Max output | 131,072 tokens | 256,000 tokens (best) | 8,192 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | No | No |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | No | Yeslow · high | No |
| Tool calling | Yes | Yes | Yes |
| Structured output | Yes | No | No |
| Availability | |||
| Weights | Open | Open | OpenApache-2.0 |
| API model ID | ibm/granite-4-h-small | step-3.5-flash | — |
| API providers | 1 | 8 (best) | 1 |
| Released | Oct 2, 2025 | Jan 29, 2026 | Sep 2, 2025 |
| Knowledge cutoff | — | Jan 2025 | Sep 2025 |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- Granite-4.0-H-Small$1.17
- Step 3.5 Flash$1.60
- Apertus 8B$1.40
Which should you choose?
Which is better: Granite-4.0-H-Small, Step 3.5 Flash or Apertus 8B?
It is close. Our weighted score puts them within a point (Granite-4.0-H-Small 63/100, Step 3.5 Flash 62/100, Apertus 8B 56/100), so choose by what matters most for your work: Granite-4.0-H-Small on price and Step 3.5 Flash for long inputs. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
Which is cheaper, Granite-4.0-H-Small, Step 3.5 Flash or Apertus 8B?
Granite-4.0-H-Small is cheaper at $0.064 input / $0.265 output per million tokens (official watsonx.ai API price). Apertus 8B costs $0.10 input / $0.20 output per million tokens (median across 1 API provider); Step 3.5 Flash costs $0.10 input / $0.30 output per million tokens (official StepFun (Global) API price). At a typical mix of three input tokens to one output token, that is $0.114 per million tokens for Granite-4.0-H-Small versus $0.125 for Apertus 8B (1.1× as much) and $0.15 for Step 3.5 Flash (1.3× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Granite-4.0-H-Small has not been scored yet, Step 3.5 Flash has not been scored yet and Apertus 8B has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Granite-4.0-H-Small, Step 3.5 Flash and Apertus 8B yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. All three support tool calling for agent workflows.
Which has the bigger context window?
Step 3.5 Flash has the largest context window at 256,000 tokens, against 131,072 for Granite-4.0-H-Small and 65,536 for Apertus 8B. Maximum output per response: Granite-4.0-H-Small up to 131,072, Step 3.5 Flash up to 256,000, Apertus 8B up to 8,192 tokens.
Which can read images, PDFs, audio or video?
Granite-4.0-H-Small accepts text; Step 3.5 Flash accepts text; Apertus 8B accepts text. They handle the same number of input types.
Are any of these open source?
Yes, all three publish their weights (Apache-2.0), so you can self-host them.
Which is newer?
Step 3.5 Flash is the newest, released Jan 29, 2026. Granite-4.0-H-Small came out Oct 2, 2025; Apertus 8B came out Sep 2, 2025. Knowledge cutoff: Step 3.5 Flash Jan 2025, Apertus 8B Sep 2025.
How do you decide the winner?
Each model gets a 0–100 score on capability (50%, independent benchmark results); price (25%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (15%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (10%, maximum tokens per request, log scale). Dimensions missing for any model are dropped and the remaining weights rescaled, so every model is judged on the same evidence. Specs and prices come from public model listings and the labs’ own API pages; capability scores come from independent benchmark runs. Data updated Oct 4, 2026.
