Granite-4.0-H-Small vs Ministral 3 3B vs Nemotron 3 Nano 30B A3B
Ministral 3 3B comes out ahead, 72 to 64 and 61 on our weighted score, and it is the cheaper option too.
IBMGranite-4.0-H-Small
61/100- ECI—
- Price$0.064 / $0.265
- Context131K
- Our pick
Mistral AIMinistral 3 3B
72/100- ECI—
- Price$0.10 / $0.10
- Context262K
NVIDIANemotron 3 Nano 30B A3B
64/100- ECI—
- Price$0.06 / $0.24
- Context262K
Ministral 3 3B is our pick
Ministral 3 3B is the better all-round choice, scoring 72/100 against Nemotron 3 Nano 30B A3B (64) and Granite-4.0-H-Small (61). It leads on inputs & features. 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 priceMinistral 3 3BMinistral 3 3B $0.10 · Nemotron 3 Nano 30B A3B $0.105 · Granite-4.0-H-Small $0.114 per 1M tokens (3:1 blend)
- Longest contextMinistral 3 3B and Nemotron 3 Nano 30B A3BMinistral 3 3B 262,144 · Nemotron 3 Nano 30B A3B 262,144 · Granite-4.0-H-Small 131,072 tokens
- Widest inputsMinistral 3 3BGranite-4.0-H-Small: Text · Ministral 3 3B: Text, Images · Nemotron 3 Nano 30B A3B: Text
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | Granite-4.0-H-Small | Ministral 3 3B | Nemotron 3 Nano 30B A3B |
|---|---|---|---|---|
| Price | 50% | 91 | 93 | 92 |
| Inputs & features | 30% | 35 | 60 | 35 |
| Context window | 20% | 25 | 37 | 37 |
| Overall | 100% | 61/100 | 72/100 | 64/100 |
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 | Ministral 3 3BMistral AI | Nemotron 3 Nano 30B A3BNVIDIA |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.064 | $0.10 | $0.06 (best) |
| Output | $0.265 | $0.10 (best) | $0.24 |
| Cached input | — | $0.01 | — |
| Blended (3:1) | $0.114 | $0.10 (best) | $0.105 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official watsonx.ai API | Official Mistral API | Median of 15 providers |
| Limits | |||
| Context window | 131,072 tokens | 262,144 tokens (best) | 262,144 tokens (best) |
| Max output | 131,072 tokens | 262,144 tokens (best) | 262,144 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | Yes | No |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | No | No | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | Yes | Yes | No |
| Availability | |||
| Weights | Open | OpenApache 2.0 | Open |
| API model ID | ibm/granite-4-h-small | ministral-3b-2512 | — |
| API providers | 1 | 11 | 16 (best) |
| Released | Oct 2, 2025 | Dec 2, 2025 | Dec 15, 2025 |
| Knowledge cutoff | — | — | Jun 25, 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
- Ministral 3 3B$1.20
- Nemotron 3 Nano 30B A3B$1.08
Which should you choose?
Which is better: Granite-4.0-H-Small, Ministral 3 3B or Nemotron 3 Nano 30B A3B?
Ministral 3 3B is the better all-round choice, scoring 72/100 against Nemotron 3 Nano 30B A3B (64) and Granite-4.0-H-Small (61). It leads on inputs & features. 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, Ministral 3 3B or Nemotron 3 Nano 30B A3B?
Ministral 3 3B is cheaper at $0.10 input / $0.10 output per million tokens (official Mistral API price). Nemotron 3 Nano 30B A3B costs $0.06 input / $0.24 output per million tokens (median across 15 API providers); Granite-4.0-H-Small costs $0.064 input / $0.265 output per million tokens (official watsonx.ai API price). At a typical mix of three input tokens to one output token, that is $0.10 per million tokens for Ministral 3 3B versus $0.105 for Nemotron 3 Nano 30B A3B (1× as much) and $0.114 for Granite-4.0-H-Small (1.1× 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, Ministral 3 3B has not been scored yet and Nemotron 3 Nano 30B A3B has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Granite-4.0-H-Small, Ministral 3 3B and Nemotron 3 Nano 30B A3B 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?
Ministral 3 3B and Nemotron 3 Nano 30B A3B have the largest context windows (262,144 and 262,144 tokens), against 131,072 for Granite-4.0-H-Small. Maximum output per response: Granite-4.0-H-Small up to 131,072, Ministral 3 3B up to 262,144, Nemotron 3 Nano 30B A3B up to 262,144 tokens.
Which can read images, PDFs, audio or video?
Granite-4.0-H-Small accepts text; Ministral 3 3B accepts text and images; Nemotron 3 Nano 30B A3B accepts text. Ministral 3 3B handles the widest range of inputs.
Are any of these open source?
Yes, all three publish their weights (Apache 2.0), so you can self-host them.
Which is newer?
Nemotron 3 Nano 30B A3B is the newest, released Dec 15, 2025. Ministral 3 3B came out Dec 2, 2025; Granite-4.0-H-Small came out Oct 2, 2025. Knowledge cutoff: Nemotron 3 Nano 30B A3B Jun 25, 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 Nov 2, 2026.
