Rnj-1 Instruct vs Granite-4.0-H-Small vs Ministral 3 8B
Ministral 3 8B comes out ahead, 68 to 61 and 50 on our weighted score, though Granite-4.0-H-Small is 24% cheaper per token.
Essential AI
Rnj-1 Instruct
50/100- ECI—
- Price$0.15 / $0.15
- Context33K
IBMGranite-4.0-H-Small
61/100- ECI—
- Price$0.064 / $0.265
- Context131K
- Our pick
Mistral AIMinistral 3 8B
68/100- ECI—
- Price$0.15 / $0.15
- Context262K
Ministral 3 8B is our pick
Ministral 3 8B is the better all-round choice, scoring 68/100 against Granite-4.0-H-Small (61) and Rnj-1 Instruct (50). It leads on inputs & features and context window. Granite-4.0-H-Small wins on price. 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 3 8B $0.15 per 1M tokens (3:1 blend)
- Longest contextMinistral 3 8BMinistral 3 8B 262,144 · Granite-4.0-H-Small 131,072 · Rnj-1 Instruct 32,768 tokens
- Widest inputsMinistral 3 8BRnj-1 Instruct: Text · Granite-4.0-H-Small: Text · Ministral 3 8B: Text, Images
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | Rnj-1 Instruct | Granite-4.0-H-Small | Ministral 3 8B |
|---|---|---|---|---|
| Price | 50% | 85 | 91 | 85 |
| Inputs & features | 30% | 25 | 35 | 60 |
| Context window | 20% | 0 | 25 | 37 |
| Overall | 100% | 50/100 | 61/100 | 68/100 |
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 | Rnj-1 InstructEssential AI | Granite-4.0-H-SmallIBM | Ministral 3 8BMistral AI |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.15 | $0.064 (best) | $0.15 |
| Output | $0.15 (best) | $0.265 | $0.15 (best) |
| Cached input | — | — | $0.015 |
| Blended (3:1) | $0.15 | $0.114 (best) | $0.15 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 1 providers | Official watsonx.ai API | Official Mistral API |
| Limits | |||
| Context window | 32,768 tokens | 131,072 tokens | 262,144 tokens (best) |
| Max output | 32,768 tokens | 131,072 tokens | 262,144 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | No | Yes |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | No | No | No |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | Yes | Yes |
| Availability | |||
| Weights | OpenApache 2.0 | Open | OpenApache 2.0 |
| API model ID | — | ibm/granite-4-h-small | ministral-8b-2512 |
| API providers | 1 | 1 | 11 (best) |
| Released | Dec 4, 2025 | Oct 2, 2025 | Dec 2, 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.
- Rnj-1 Instruct$1.80
- Granite-4.0-H-Small$1.17
- Ministral 3 8B$1.80
Which should you choose?
Which is better: Rnj-1 Instruct, Granite-4.0-H-Small or Ministral 3 8B?
Ministral 3 8B is the better all-round choice, scoring 68/100 against Granite-4.0-H-Small (61) and Rnj-1 Instruct (50). It leads on inputs & features and context window. Granite-4.0-H-Small wins on price. 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, Rnj-1 Instruct, Granite-4.0-H-Small or Ministral 3 8B?
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 3 8B costs $0.15 input / $0.15 output per million tokens (official Mistral 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 $0.15 for Rnj-1 Instruct (1.3× as much) and $0.15 for Ministral 3 8B (1.3× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Rnj-1 Instruct has not been scored yet, Granite-4.0-H-Small has not been scored yet and Ministral 3 8B has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Rnj-1 Instruct, Granite-4.0-H-Small and Ministral 3 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?
Ministral 3 8B 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: Rnj-1 Instruct up to 32,768, Granite-4.0-H-Small up to 131,072, Ministral 3 8B up to 262,144 tokens.
Which can read images, PDFs, audio or video?
Rnj-1 Instruct accepts text; Granite-4.0-H-Small accepts text; Ministral 3 8B accepts text and images. Ministral 3 8B 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?
Rnj-1 Instruct is the newest, released Dec 4, 2025. Ministral 3 8B 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.
