Ministral 3 8B vs Gemma 3 27B IT vs Rnj-1 Instruct
Ministral 3 8B comes out ahead, 68 to 62 and 50 on our weighted score.
- Our pick
Mistral AIMinistral 3 8B
68/100- ECI—
- Price$0.15 / $0.15
- Context262K
GoogleGemma 3 27B IT
62/100- ECI129.9
- Price$0.11 / $0.30
- Context131K
Essential AI
Rnj-1 Instruct
50/100- ECI—
- Price$0.15 / $0.15
- Context33K
Ministral 3 8B is our pick
Ministral 3 8B is the better all-round choice, scoring 68/100 against Gemma 3 27B IT (62) and Rnj-1 Instruct (50). It leads on inputs & features and context window. 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 8B and Rnj-1 InstructMinistral 3 8B $0.15 · Rnj-1 Instruct $0.15 · Gemma 3 27B IT $0.157 per 1M tokens (3:1 blend)
- Longest contextMinistral 3 8BMinistral 3 8B 262,144 · Gemma 3 27B IT 131,072 · Rnj-1 Instruct 32,768 tokens
- Widest inputsMinistral 3 8B and Gemma 3 27B ITMinistral 3 8B: Text, Images · Gemma 3 27B IT: Text, Images · Rnj-1 Instruct: Text
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | Ministral 3 8B | Gemma 3 27B IT | Rnj-1 Instruct |
|---|---|---|---|---|
| Price | 50% | 85 | 84 | 85 |
| Inputs & features | 30% | 60 | 50 | 25 |
| Context window | 20% | 37 | 25 | 0 |
| Overall | 100% | 68/100 | 62/100 | 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 | Ministral 3 8BMistral AI | Gemma 3 27B ITGoogle | Rnj-1 InstructEssential AI |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | 129.9 | — |
| ECI rank | — | #137 of 165 | — |
| GPQA DiamondGraduate-level science questions | — | 47.7% | — |
| OTIS Mock AIME 2024–2025Competition mathematics | — | 22.5% | — |
| Price per million tokens | |||
| Input | $0.15 | $0.11 (best) | $0.15 |
| Output | $0.15 (best) | $0.30 | $0.15 (best) |
| Cached input | $0.015 | — | — |
| Blended (3:1) | $0.15 (best) | $0.157 | $0.15 (best) |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official Mistral API | Median of 16 providers | Median of 1 providers |
| Limits | |||
| Context window | 262,144 tokens (best) | 131,072 tokens | 32,768 tokens |
| Max output | 262,144 tokens (best) | 131,072 tokens | 32,768 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | 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 | OpenApache 2.0 | Open | OpenApache 2.0 |
| API model ID | ministral-8b-2512 | — | — |
| API providers | 11 | 17 (best) | 1 |
| Released | Dec 2, 2025 | Mar 12, 2025 | Dec 4, 2025 |
| Knowledge cutoff | — | Aug 2024 | — |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- Ministral 3 8B$1.80
- Gemma 3 27B IT$1.69
- Rnj-1 Instruct$1.80
Which should you choose?
Which is better: Ministral 3 8B, Gemma 3 27B IT or Rnj-1 Instruct?
Ministral 3 8B is the better all-round choice, scoring 68/100 against Gemma 3 27B IT (62) and Rnj-1 Instruct (50). It leads on inputs & features and context window. 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, Ministral 3 8B, Gemma 3 27B IT or Rnj-1 Instruct?
Ministral 3 8B is cheaper at $0.15 input / $0.15 output per million tokens (official Mistral API price). Rnj-1 Instruct costs $0.15 input / $0.15 output per million tokens (median across 1 API provider); Gemma 3 27B IT costs $0.11 input / $0.30 output per million tokens (median across 16 API providers). At a typical mix of three input tokens to one output token, that is $0.15 per million tokens for Ministral 3 8B versus $0.15 for Rnj-1 Instruct (1× as much) and $0.157 for Gemma 3 27B IT (1× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Ministral 3 8B has not been scored yet, Gemma 3 27B IT has an ECI of 129.9 and Rnj-1 Instruct has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Ministral 3 8B, Gemma 3 27B IT 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 3 8B has the largest context window at 262,144 tokens, against 131,072 for Gemma 3 27B IT and 32,768 for Rnj-1 Instruct. Maximum output per response: Ministral 3 8B up to 262,144, Gemma 3 27B IT up to 131,072, Rnj-1 Instruct up to 32,768 tokens.
Which can read images, PDFs, audio or video?
Ministral 3 8B accepts text and images; Gemma 3 27B IT accepts text and images; Rnj-1 Instruct accepts text. 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; Gemma 3 27B IT came out Mar 12, 2025. Knowledge cutoff: Gemma 3 27B IT Aug 2024.
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.
