Gemma 4 12B IT vs Gemma 4 31B IT vs Laguna S 2.1
Gemma 4 12B IT comes out ahead, 75 to 70 and 69 on our weighted score.
- Our pick
GoogleGemma 4 12B IT
75/100- ECI—
- Price$0.075 / $0.275
- Context262K
- Google
Gemma 4 31B IT
70/100- ECI142.8
- Price$0.14 / $0.40
- Context262K
PoolsideLaguna S 2.1
69/100- ECI—
- Price$0.10 / $0.20
- Context1.05M
Gemma 4 12B IT is our pick
Gemma 4 12B IT is the better all-round choice, scoring 75/100 against Gemma 4 31B IT (70) and Laguna S 2.1 (69). Laguna S 2.1 wins 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 priceGemma 4 12B IT and Laguna S 2.1Gemma 4 12B IT $0.125 · Laguna S 2.1 $0.125 · Gemma 4 31B IT $0.205 per 1M tokens (3:1 blend)
- Longest contextLaguna S 2.1Laguna S 2.1 1,048,576 · Gemma 4 12B IT 262,144 · Gemma 4 31B IT 262,144 tokens
- Widest inputsGemma 4 12B IT and Gemma 4 31B ITGemma 4 12B IT: Text, Images · Gemma 4 31B IT: Text, Images · Laguna S 2.1: Text
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | Gemma 4 12B IT | Gemma 4 31B IT | Laguna S 2.1 |
|---|---|---|---|---|
| Price | 50% | 93 | 83 | 93 |
| Inputs & features | 30% | 70 | 70 | 35 |
| Context window | 20% | 37 | 37 | 61 |
| Overall | 100% | 75/100 | 70/100 | 69/100 |
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 4 12B ITGoogle | Gemma 4 31B ITGoogle | Laguna S 2.1Poolside |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | 142.8 | — |
| ECI rank | — | #86 of 148 | — |
| GPQA DiamondGraduate-level science questions | — | 75.8% | — |
| OTIS Mock AIME 2024–2025Competition mathematics | — | 73.3% | — |
| SimpleQA VerifiedShort factual questions | — | 10.4% | — |
| Price per million tokens | |||
| Input | $0.075 (best) | $0.14 | $0.10 |
| Output | $0.275 | $0.40 | $0.20 (best) |
| Cached input | — | — | — |
| Blended (3:1) | $0.125 (best) | $0.205 | $0.125 (best) |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 2 providers | Median of 30 providers | Median of 4 providers |
| Limits | |||
| Context window | 262,144 tokens | 262,144 tokens | 1,048,576 tokens (best) |
| Max output | 32,768 tokens | 32,768 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 | Yes | Yes | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | Yes | Yes | No |
| Availability | |||
| Weights | Open | Open | Open |
| API model ID | — | gemma-4-31b-it | poolside/laguna-s-2.1 |
| API providers | 2 | 38 (best) | 6 |
| Released | Jun 9, 2026 | Apr 2, 2026 | Jul 21, 2026 |
| 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.
- Gemma 4 12B IT$1.30
- Gemma 4 31B IT$2.20
- Laguna S 2.1$1.40
Which should you choose?
Which is better: Gemma 4 12B IT, Gemma 4 31B IT or Laguna S 2.1?
Gemma 4 12B IT is the better all-round choice, scoring 75/100 against Gemma 4 31B IT (70) and Laguna S 2.1 (69). Laguna S 2.1 wins 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 4 12B IT, Gemma 4 31B IT or Laguna S 2.1?
Gemma 4 12B IT is cheaper at $0.075 input / $0.275 output per million tokens (median across 2 API providers). Laguna S 2.1 costs $0.10 input / $0.20 output per million tokens (median across 4 API providers; free on Poolside); Gemma 4 31B IT costs $0.14 input / $0.40 output per million tokens (median across 30 API providers). At a typical mix of three input tokens to one output token, that is $0.125 per million tokens for Gemma 4 12B IT versus $0.125 for Laguna S 2.1 (1× as much) and $0.205 for Gemma 4 31B IT (1.6× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Gemma 4 12B IT has not been scored yet, Gemma 4 31B IT has an ECI of 142.8 and Laguna S 2.1 has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Gemma 4 12B IT, Gemma 4 31B IT and Laguna S 2.1 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?
Laguna S 2.1 has the largest context window at 1,048,576 tokens, against 262,144 for Gemma 4 12B IT and 262,144 for Gemma 4 31B IT. Maximum output per response: Gemma 4 12B IT up to 32,768, Gemma 4 31B IT up to 32,768, Laguna S 2.1 up to 32,768 tokens.
Which can read images, PDFs, audio or video?
Gemma 4 12B IT accepts text and images; Gemma 4 31B IT accepts text and images; Laguna S 2.1 accepts text. Gemma 4 12B IT handles the widest range of inputs.
Are any of these open source?
Yes, all three publish their weights, so you can self-host them.
Which is newer?
Laguna S 2.1 is the newest, released Jul 21, 2026. Gemma 4 12B IT came out Jun 9, 2026; Gemma 4 31B IT came out Apr 2, 2026.
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 Oct 4, 2026.
