DiffusionGemma 26B A4B IT vs Gemma 4 E2B IT vs Hy-MT2-1.8B
Too close to call on our weighted score (Gemma 4 E2B IT 76, DiffusionGemma 26B A4B IT 75, Hy-MT2-1.8B 49). The right pick depends on what you value most.
GoogleDiffusionGemma 26B A4B IT
75/100- ECI—
- Price$0.05 / $0.15
- Context262K
- Google
Gemma 4 E2B IT
76/100- ECI—
- Price$0.04 / $0.08
- Context131K
TencentHy-MT2-1.8B
49/100- ECI—
- Price$0.044 / $0.177
- Context8K
Too close to call
It is close. Our weighted score puts them within 1 points (Gemma 4 E2B IT 76/100, DiffusionGemma 26B A4B IT 75/100, Hy-MT2-1.8B 49/100), so choose by what matters most for your work: Gemma 4 E2B IT on price and DiffusionGemma 26B A4B IT 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 priceGemma 4 E2B ITGemma 4 E2B IT $0.05 · DiffusionGemma 26B A4B IT $0.075 · Hy-MT2-1.8B $0.077 per 1M tokens (3:1 blend)
- Longest contextDiffusionGemma 26B A4B ITDiffusionGemma 26B A4B IT 262,144 · Gemma 4 E2B IT 131,072 · Hy-MT2-1.8B 8,192 tokens
- Widest inputsGemma 4 E2B ITDiffusionGemma 26B A4B IT: Text, Images · Gemma 4 E2B IT: Text, Images, Audio · Hy-MT2-1.8B: Text
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | DiffusionGemma 26B A4B IT | Gemma 4 E2B IT | Hy-MT2-1.8B |
|---|---|---|---|---|
| Price | 50% | 99 | 100 | 98 |
| Inputs & features | 30% | 60 | 70 | 0 |
| Context window | 20% | 37 | 25 | 0 |
| Overall | 100% | 75/100 | 76/100 | 49/100 |
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 | DiffusionGemma 26B A4B ITGoogle | Gemma 4 E2B ITGoogle | Hy-MT2-1.8BTencent |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.05 | $0.04 (best) | $0.044 |
| Output | $0.15 | $0.08 (best) | $0.177 |
| Cached input | — | — | — |
| Blended (3:1) | $0.075 | $0.05 (best) | $0.077 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 1 providers | Median of 1 providers | Median of 3 providers |
| Limits | |||
| Context window | 262,144 tokens (best) | 131,072 tokens | 8,192 tokens |
| Max output | 32,768 tokens (best) | 8,192 tokens | 4,096 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | Yes | No |
| PDFs | No | No | No |
| Audio | No | Yes | No |
| Video | No | No | No |
| Reasoning | Yes | Yes | No |
| Tool calling | Yes | Yes | No |
| Structured output | No | No | No |
| Availability | |||
| Weights | OpenApache 2.0 | Open | Open |
| API model ID | — | — | — |
| API providers | 2 | 1 | 3 (best) |
| Released | Jun 9, 2026 | Apr 2, 2026 | May 21, 2026 |
| Knowledge cutoff | Jan 2025 | — | — |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- DiffusionGemma 26B A4B IT$0.80
- Gemma 4 E2B IT$0.56
- Hy-MT2-1.8B$0.794
Which should you choose?
Which is better: DiffusionGemma 26B A4B IT, Gemma 4 E2B IT or Hy-MT2-1.8B?
It is close. Our weighted score puts them within 1 points (Gemma 4 E2B IT 76/100, DiffusionGemma 26B A4B IT 75/100, Hy-MT2-1.8B 49/100), so choose by what matters most for your work: Gemma 4 E2B IT on price and DiffusionGemma 26B A4B IT 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, DiffusionGemma 26B A4B IT, Gemma 4 E2B IT or Hy-MT2-1.8B?
Gemma 4 E2B IT is cheaper at $0.04 input / $0.08 output per million tokens (median across 1 API provider). DiffusionGemma 26B A4B IT costs $0.05 input / $0.15 output per million tokens (median across 1 API provider); Hy-MT2-1.8B costs $0.044 input / $0.177 output per million tokens (median across 3 API providers). At a typical mix of three input tokens to one output token, that is $0.05 per million tokens for Gemma 4 E2B IT versus $0.075 for DiffusionGemma 26B A4B IT (1.5× as much) and $0.077 for Hy-MT2-1.8B (1.5× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. DiffusionGemma 26B A4B IT has not been scored yet, Gemma 4 E2B IT has not been scored yet and Hy-MT2-1.8B has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for DiffusionGemma 26B A4B IT, Gemma 4 E2B IT and Hy-MT2-1.8B yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that Hy-MT2-1.8B does not support tool calling, which most coding agents need.
Which has the bigger context window?
DiffusionGemma 26B A4B IT has the largest context window at 262,144 tokens, against 131,072 for Gemma 4 E2B IT and 8,192 for Hy-MT2-1.8B. Maximum output per response: DiffusionGemma 26B A4B IT up to 32,768, Gemma 4 E2B IT up to 8,192, Hy-MT2-1.8B up to 4,096 tokens.
Which can read images, PDFs, audio or video?
DiffusionGemma 26B A4B IT accepts text and images; Gemma 4 E2B IT accepts text, images and audio; Hy-MT2-1.8B accepts text. Gemma 4 E2B IT 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?
DiffusionGemma 26B A4B IT is the newest, released Jun 9, 2026. Hy-MT2-1.8B came out May 21, 2026; Gemma 4 E2B IT came out Apr 2, 2026. Knowledge cutoff: DiffusionGemma 26B A4B IT Jan 2025.
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.
