Gemma 3 27B IT vs Mistral Small 3.2 24B vs Llama 4 Scout 17B Instruct
Llama 4 Scout 17B Instruct comes out ahead, 72 to 65 and 62 on our weighted score, though Mistral Small 3.2 24B is 45% cheaper per token.
GoogleGemma 3 27B IT
62/100- ECI129.9
- Price$0.11 / $0.30
- Context131K
Mistral AIMistral Small 3.2 24B
65/100- ECI—
- Price$0.10 / $0.305
- Context256K
- Our pick
MetaLlama 4 Scout 17B Instruct
72/100- ECI129.6
- Price$0.17 / $0.59
- Context10M
Llama 4 Scout 17B Instruct is our pick
Llama 4 Scout 17B Instruct is the better all-round choice, scoring 72/100 against Mistral Small 3.2 24B (65) and Gemma 3 27B IT (62). It leads on 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 priceMistral Small 3.2 24BMistral Small 3.2 24B $0.151 · Gemma 3 27B IT $0.157 · Llama 4 Scout 17B Instruct $0.275 per 1M tokens (3:1 blend)
- Longest contextLlama 4 Scout 17B InstructLlama 4 Scout 17B Instruct 10,000,000 · Mistral Small 3.2 24B 256,000 · Gemma 3 27B IT 131,072 tokens
- Widest inputsSame inputsGemma 3 27B IT: Text, Images · Mistral Small 3.2 24B: Text, Images · Llama 4 Scout 17B Instruct: Text, Images
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | Gemma 3 27B IT | Mistral Small 3.2 24B | Llama 4 Scout 17B Instruct |
|---|---|---|---|---|
| Price | 50% | 84 | 85 | 73 |
| Inputs & features | 30% | 50 | 50 | 50 |
| Context window | 20% | 25 | 36 | 100 |
| Overall | 100% | 62/100 | 65/100 | 72/100 |
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 | Gemma 3 27B ITGoogle | Mistral Small 3.2 24BMistral AI | Llama 4 Scout 17B InstructMeta |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 129.9 (best) | — | 129.6 |
| ECI rank | #137 of 165 (best) | — | #138 of 165 |
| GPQA DiamondGraduate-level science questions | 47.7% | — | 51.8% (best) |
| OTIS Mock AIME 2024–2025Competition mathematics | 22.5% (best) | — | 7.8% |
| Price per million tokens | |||
| Input | $0.11 | $0.10 (best) | $0.17 |
| Output | $0.30 (best) | $0.305 | $0.59 |
| Cached input | — | — | — |
| Blended (3:1) | $0.157 | $0.151 (best) | $0.275 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 16 providers | Median of 8 providers | Median of 13 providers |
| Limits | |||
| Context window | 131,072 tokens | 256,000 tokens | 10,000,000 tokens (best) |
| Max output | 131,072 tokens (best) | 16,384 tokens | 16,384 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | Yes | 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 | No | No |
| Availability | |||
| Weights | Open | Open | Open |
| API model ID | — | — | — |
| API providers | 17 (best) | 8 | 13 |
| Released | Mar 12, 2025 | Jun 20, 2025 | Apr 5, 2025 |
| Knowledge cutoff | Aug 2024 | Oct 31, 2023 | 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.
- Gemma 3 27B IT$1.69
- Mistral Small 3.2 24B$1.61
- Llama 4 Scout 17B Instruct$2.88
Which should you choose?
Which is better: Gemma 3 27B IT, Mistral Small 3.2 24B or Llama 4 Scout 17B Instruct?
Llama 4 Scout 17B Instruct is the better all-round choice, scoring 72/100 against Mistral Small 3.2 24B (65) and Gemma 3 27B IT (62). It leads on 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, Gemma 3 27B IT, Mistral Small 3.2 24B or Llama 4 Scout 17B Instruct?
Mistral Small 3.2 24B is cheaper at $0.10 input / $0.305 output per million tokens (median across 8 API providers). Gemma 3 27B IT costs $0.11 input / $0.30 output per million tokens (median across 16 API providers); Llama 4 Scout 17B Instruct costs $0.17 input / $0.59 output per million tokens (median across 13 API providers). At a typical mix of three input tokens to one output token, that is $0.151 per million tokens for Mistral Small 3.2 24B versus $0.157 for Gemma 3 27B IT (1× as much) and $0.275 for Llama 4 Scout 17B Instruct (1.8× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Gemma 3 27B IT has an ECI of 129.9, Mistral Small 3.2 24B has not been scored yet and Llama 4 Scout 17B Instruct has an ECI of 129.6.
Which is better for coding?
There are no published SWE-bench Verified results for Gemma 3 27B IT, Mistral Small 3.2 24B and Llama 4 Scout 17B 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?
Llama 4 Scout 17B Instruct has the largest context window at 10,000,000 tokens, against 256,000 for Mistral Small 3.2 24B and 131,072 for Gemma 3 27B IT. Maximum output per response: Gemma 3 27B IT up to 131,072, Mistral Small 3.2 24B up to 16,384, Llama 4 Scout 17B Instruct up to 16,384 tokens.
Which can read images, PDFs, audio or video?
Gemma 3 27B IT accepts text and images; Mistral Small 3.2 24B accepts text and images; Llama 4 Scout 17B Instruct accepts text and images. They handle the same number of input types.
Are any of these open source?
Yes, all three publish their weights, so you can self-host them.
Which is newer?
Mistral Small 3.2 24B is the newest, released Jun 20, 2025. Llama 4 Scout 17B Instruct came out Apr 5, 2025; Gemma 3 27B IT came out Mar 12, 2025. Knowledge cutoff: Gemma 3 27B IT Aug 2024, Mistral Small 3.2 24B Oct 31, 2023, Llama 4 Scout 17B Instruct 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.
