Gemma 3 4B IT vs Llama-3.2-1B vs Mistral 7B Instruct v0.3
Gemma 3 4B IT comes out ahead, 24 to 11 and 10 on our weighted score, and it is the cheaper option too.
- Our pick
GoogleGemma 3 4B IT
24/100- ECI115.8
- Price$0.05 / $0.10
- Context131K
MetaLlama-3.2-1B
11/100- ECI—
- Price$0.027 / $0.201
- Context131K
Mistral AIMistral 7B Instruct v0.3
10/100- ECI109.0
- Price—
- Context33K
Gemma 3 4B IT is our pick
Gemma 3 4B IT is the better all-round choice, scoring 24/100 against Llama-3.2-1B (11) and Mistral 7B Instruct v0.3 (10). It leads on capability and inputs & features. The score weighs capability 67%, inputs & features 20%, context window 13%. Capability uses the average of shared benchmarks (GPQA Diamond and OTIS Mock AIME 2024–2025), because Llama-3.2-1B has no Capabilities Index score yet.
- CapabilityGemma 3 4B ITShared benchmarks: Gemma 3 4B IT 15.4% · Llama-3.2-1B 12.2% · Mistral 7B Instruct v0.3 7.7%
- Lowest priceGemma 3 4B ITGemma 3 4B IT $0.063 · Llama-3.2-1B $0.07 per 1M tokens (3:1 blend) · Mistral 7B Instruct v0.3 unpriced
- Longest contextGemma 3 4B IT and Llama-3.2-1BGemma 3 4B IT 131,072 · Llama-3.2-1B 131,072 · Mistral 7B Instruct v0.3 32,768 tokens
- Widest inputsGemma 3 4B ITGemma 3 4B IT: Text, Images · Llama-3.2-1B: Text · Mistral 7B Instruct v0.3: Text
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | Gemma 3 4B IT | Llama-3.2-1B | Mistral 7B Instruct v0.3 |
|---|---|---|---|---|
| CapabilityShared benchmarks | 67% | 15 | 12 | 8 |
| Inputs & features | 20% | 50 | 0 | 25 |
| Context window | 13% | 25 | 25 | 0 |
| Overall | 100% | 24/100 | 11/100 | 10/100 |
Left out because at least one model lacks the data: price. 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 4B ITGoogle | Llama-3.2-1BMeta | Mistral 7B Instruct v0.3Mistral AI |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 115.8 (best) | — | 109.0 |
| ECI rank | #163 of 165 (best) | — | #164 of 165 |
| GPQA DiamondGraduate-level science questions | 23.2% | 23.9% (best) | 15.2% |
| OTIS Mock AIME 2024–2025Competition mathematics | 7.5% (best) | 0.6% | 0.3% |
| Price per million tokens | |||
| Input | $0.05 | $0.027 (best) | — |
| Output | $0.10 (best) | $0.201 | — |
| Cached input | — | — | — |
| Blended (3:1) | $0.063 (best) | $0.07 | — |
| Long-context rate | Same rate | Same rate | — |
| Price source | Median of 9 providers | Median of 6 providers | — |
| Limits | |||
| Context window | 131,072 tokens (best) | 131,072 tokens (best) | 32,768 tokens |
| Max output | 131,072 tokens (best) | 8,192 tokens | 32,768 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | No | No |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | No | No | No |
| Tool calling | Yes | No | Yes |
| Structured output | No | No | No |
| Availability | |||
| Weights | Open | OpenLlama 3.2 Community License | OpenApache 2.0 |
| API model ID | — | — | — |
| API providers | 10 (best) | 6 | 1 |
| Released | Mar 12, 2025 | Sep 25, 2024 | May 22, 2024 |
| Knowledge cutoff | Aug 2024 | Dec 2023 | — |
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 4B IT$0.70
- Llama-3.2-1B$0.672
- Mistral 7B Instruct v0.3—
Which should you choose?
Which is better: Gemma 3 4B IT, Llama-3.2-1B or Mistral 7B Instruct v0.3?
Gemma 3 4B IT is the better all-round choice, scoring 24/100 against Llama-3.2-1B (11) and Mistral 7B Instruct v0.3 (10). It leads on capability and inputs & features. The score weighs capability 67%, inputs & features 20%, context window 13%. Capability uses the average of shared benchmarks (GPQA Diamond and OTIS Mock AIME 2024–2025), because Llama-3.2-1B has no Capabilities Index score yet.
Which is cheaper, Gemma 3 4B IT, Llama-3.2-1B or Mistral 7B Instruct v0.3?
Gemma 3 4B IT is cheaper at $0.05 input / $0.10 output per million tokens (median across 9 API providers). Llama-3.2-1B costs $0.027 input / $0.201 output per million tokens (median across 6 API providers). At a typical mix of three input tokens to one output token, that is $0.063 per million tokens for Gemma 3 4B IT versus $0.07 for Llama-3.2-1B (1.1× as much). Mistral 7B Instruct v0.3 has no published per-token price.
Which scores higher on benchmarks?
Not every model here has a Capabilities Index score, so we compare the average of shared benchmarks (GPQA Diamond and OTIS Mock AIME 2024–2025): Gemma 3 4B IT 15.4%, Llama-3.2-1B 12.2% and Mistral 7B Instruct v0.3 7.7%. On individual benchmarks: GPQA Diamond — Llama-3.2-1B 23.9%, Gemma 3 4B IT 23.2%, Mistral 7B Instruct v0.3 15.2%; OTIS Mock AIME 2024–2025 — Gemma 3 4B IT 7.5%, Llama-3.2-1B 0.6%, Mistral 7B Instruct v0.3 0.3%.
Which is better for coding?
There are no published SWE-bench Verified results for Gemma 3 4B IT, Llama-3.2-1B and Mistral 7B Instruct v0.3 yet, so there is no like-for-like coding score. On overall capability, Gemma 3 4B IT leads, which tends to carry over to coding, but test on your own codebase. Note that Llama-3.2-1B does not support tool calling, which most coding agents need.
Which has the bigger context window?
Gemma 3 4B IT and Llama-3.2-1B have the largest context windows (131,072 and 131,072 tokens), against 32,768 for Mistral 7B Instruct v0.3. Maximum output per response: Gemma 3 4B IT up to 131,072, Llama-3.2-1B up to 8,192, Mistral 7B Instruct v0.3 up to 32,768 tokens.
Which can read images, PDFs, audio or video?
Gemma 3 4B IT accepts text and images; Llama-3.2-1B accepts text; Mistral 7B Instruct v0.3 accepts text. Gemma 3 4B IT handles the widest range of inputs.
Are any of these open source?
Yes, all three publish their weights (Llama 3.2 Community License and Apache 2.0), so you can self-host them.
Which is newer?
Gemma 3 4B IT is the newest, released Mar 12, 2025. Llama-3.2-1B came out Sep 25, 2024; Mistral 7B Instruct v0.3 came out May 22, 2024. Knowledge cutoff: Gemma 3 4B IT Aug 2024, Llama-3.2-1B Dec 2023.
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.
