Gemma 4 12B IT vs Hy-MT2-30B-A3B vs Laguna S 2.1
Too close to call on our weighted score (Gemma 4 12B IT 70, Laguna S 2.1 68, Hy-MT2-30B-A3B 44). The right pick depends on what you value most.
GoogleGemma 4 12B IT
70/100- ECI—
- Price$0.075 / $0.275
- Context262K
TencentHy-MT2-30B-A3B
44/100- ECI—
- Price$0.074 / $0.295
- Context8K
PoolsideLaguna S 2.1
68/100- ECI—
- Price$0.09 / $0.18
- Context1.05M
Too close to call
It is close. Our weighted score puts them within 2 points (Gemma 4 12B IT 70/100, Laguna S 2.1 68/100, Hy-MT2-30B-A3B 44/100), so choose by what matters most for your work: Laguna S 2.1 on price and Laguna S 2.1 for long inputs. 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 priceLaguna S 2.1Laguna S 2.1 $0.113 · Gemma 4 12B IT $0.125 · Hy-MT2-30B-A3B $0.129 per 1M tokens (3:1 blend)
- Longest contextLaguna S 2.1Laguna S 2.1 1,048,576 · Gemma 4 12B IT 262,144 · Hy-MT2-30B-A3B 8,192 tokens
- Widest inputsGemma 4 12B ITGemma 4 12B IT: Text, Images · Hy-MT2-30B-A3B: Text · 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 | Hy-MT2-30B-A3B | Laguna S 2.1 |
|---|---|---|---|---|
| Price | 50% | 89 | 88 | 91 |
| Inputs & features | 30% | 60 | 0 | 35 |
| Context window | 20% | 37 | 0 | 61 |
| Overall | 100% | 70/100 | 44/100 | 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 | Gemma 4 12B ITGoogle | Hy-MT2-30B-A3BTencent | Laguna S 2.1Poolside |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.075 | $0.074 (best) | $0.09 |
| Output | $0.275 | $0.295 | $0.18 (best) |
| Cached input | — | — | — |
| Blended (3:1) | $0.125 | $0.129 | $0.113 (best) |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 2 providers | Median of 3 providers | Median of 2 providers |
| Limits | |||
| Context window | 262,144 tokens | 8,192 tokens | 1,048,576 tokens (best) |
| Max output | 32,768 tokens (best) | 4,096 tokens | 32,768 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | No | No |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | Yes | No | Yes |
| Tool calling | Yes | No | Yes |
| Structured output | No | No | No |
| Availability | |||
| Weights | Open | Open | Open |
| API model ID | — | — | poolside/laguna-s-2.1 |
| API providers | 2 | 3 | 4 (best) |
| Released | Jun 9, 2026 | May 21, 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
- Hy-MT2-30B-A3B$1.33
- Laguna S 2.1$1.26
Which should you choose?
Which is better: Gemma 4 12B IT, Hy-MT2-30B-A3B or Laguna S 2.1?
It is close. Our weighted score puts them within 2 points (Gemma 4 12B IT 70/100, Laguna S 2.1 68/100, Hy-MT2-30B-A3B 44/100), so choose by what matters most for your work: Laguna S 2.1 on price and Laguna S 2.1 for long inputs. 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, Hy-MT2-30B-A3B or Laguna S 2.1?
Laguna S 2.1 is cheaper at $0.09 input / $0.18 output per million tokens (median across 2 API providers; free on Poolside). Gemma 4 12B IT costs $0.075 input / $0.275 output per million tokens (median across 2 API providers); Hy-MT2-30B-A3B costs $0.074 input / $0.295 output per million tokens (median across 3 API providers). At a typical mix of three input tokens to one output token, that is $0.113 per million tokens for Laguna S 2.1 versus $0.125 for Gemma 4 12B IT (1.1× as much) and $0.129 for Hy-MT2-30B-A3B (1.1× 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, Hy-MT2-30B-A3B has not been scored yet 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, Hy-MT2-30B-A3B and Laguna S 2.1 yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that Hy-MT2-30B-A3B does not support tool calling, which most coding agents need.
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 8,192 for Hy-MT2-30B-A3B. Maximum output per response: Gemma 4 12B IT up to 32,768, Hy-MT2-30B-A3B up to 4,096, 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; Hy-MT2-30B-A3B accepts text; 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; Hy-MT2-30B-A3B came out May 21, 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 Nov 2, 2026.
