Granite-4.0-H-Small vs Ministral 14B vs Rnj-1 Instruct
Too close to call on our weighted score (Ministral 14B 63, Granite-4.0-H-Small 61, Rnj-1 Instruct 50). The right pick depends on what you value most.
IBMGranite-4.0-H-Small
61/100- ECI—
- Price$0.064 / $0.265
- Context131K
Mistral AIMinistral 14B
63/100- ECI—
- Price$0.175 / $0.175
- Context262K
Essential AI
Rnj-1 Instruct
50/100- ECI—
- Price$0.15 / $0.15
- Context33K
Too close to call
It is close. Our weighted score puts them within 3 points (Ministral 14B 63/100, Granite-4.0-H-Small 61/100, Rnj-1 Instruct 50/100), so choose by what matters most for your work: Granite-4.0-H-Small on price and Ministral 14B 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 · Rnj-1 Instruct $0.15 · Ministral 14B $0.175 per 1M tokens (3:1 blend)
- Longest contextMinistral 14BMinistral 14B 262,144 · Granite-4.0-H-Small 131,072 · Rnj-1 Instruct 32,768 tokens
- Widest inputsMinistral 14BGranite-4.0-H-Small: Text · Ministral 14B: Text, Images · Rnj-1 Instruct: Text
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | Granite-4.0-H-Small | Ministral 14B | Rnj-1 Instruct |
|---|---|---|---|---|
| Price | 50% | 91 | 82 | 85 |
| Inputs & features | 30% | 35 | 50 | 25 |
| Context window | 20% | 25 | 37 | 0 |
| Overall | 100% | 61/100 | 63/100 | 50/100 |
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 14BMistral AI | Rnj-1 InstructEssential AI |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.064 (best) | $0.175 | $0.15 |
| Output | $0.265 | $0.175 | $0.15 (best) |
| Cached input | — | — | — |
| Blended (3:1) | $0.114 (best) | $0.175 | $0.15 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official watsonx.ai API | Median of 2 providers | Median of 1 providers |
| Limits | |||
| Context window | 131,072 tokens | 262,144 tokens (best) | 32,768 tokens |
| Max output | 131,072 tokens | 262,144 tokens (best) | 32,768 tokens |
| 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 | No |
| Tool calling | Yes | Yes | Yes |
| Structured output | Yes | No | No |
| Availability | |||
| Weights | Open | OpenApache-2.0 | OpenApache 2.0 |
| API model ID | ibm/granite-4-h-small | — | — |
| API providers | 1 | 2 (best) | 1 |
| Released | Oct 2, 2025 | Dec 2, 2025 | Dec 4, 2025 |
| Knowledge cutoff | — | — | — |
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 14B$2.10
- Rnj-1 Instruct$1.80
Which should you choose?
Which is better: Granite-4.0-H-Small, Ministral 14B or Rnj-1 Instruct?
It is close. Our weighted score puts them within 3 points (Ministral 14B 63/100, Granite-4.0-H-Small 61/100, Rnj-1 Instruct 50/100), so choose by what matters most for your work: Granite-4.0-H-Small on price and Ministral 14B 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, Ministral 14B or Rnj-1 Instruct?
Granite-4.0-H-Small is cheaper at $0.064 input / $0.265 output per million tokens (official watsonx.ai API price). Rnj-1 Instruct costs $0.15 input / $0.15 output per million tokens (median across 1 API provider); Ministral 14B costs $0.175 input / $0.175 output per million tokens (median across 2 API providers). 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 $0.15 for Rnj-1 Instruct (1.3× as much) and $0.175 for Ministral 14B (1.5× 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 14B has not been scored yet and Rnj-1 Instruct 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 14B and Rnj-1 Instruct 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 14B has the largest context window at 262,144 tokens, against 131,072 for Granite-4.0-H-Small and 32,768 for Rnj-1 Instruct. Maximum output per response: Granite-4.0-H-Small up to 131,072, Ministral 14B up to 262,144, Rnj-1 Instruct up to 32,768 tokens.
Which can read images, PDFs, audio or video?
Granite-4.0-H-Small accepts text; Ministral 14B accepts text and images; Rnj-1 Instruct accepts text. Ministral 14B handles the widest range of inputs.
Are any of these open source?
Yes, all three publish their weights (Apache-2.0 and Apache 2.0), so you can self-host them.
Which is newer?
Rnj-1 Instruct is the newest, released Dec 4, 2025. Ministral 14B came out Dec 2, 2025; Granite-4.0-H-Small came out Oct 2, 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.
