DiffusionGemma 26B A4B IT vs Granite 4.2 8B vs Hy-MT2-1.8B

DiffusionGemma 26B A4B IT is the better all-round choice, scoring 75/100 against Granite 4.2 8B (64) and Hy-MT2-1.8B (49). It leads on inputs & features and 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.

DiffusionGemma 26B A4B IT is cheaper at $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); Granite 4.2 8B costs $0.06 input / $0.15 output per million tokens (median across 7 API providers). At a typical mix of three input tokens to one output token, that is $0.075 per million tokens for DiffusionGemma 26B A4B IT versus $0.077 for Hy-MT2-1.8B (1× as much) and $0.083 for Granite 4.2 8B (1.1× as much).

There is no independent benchmark that covers all three models yet. DiffusionGemma 26B A4B IT has not been scored yet, Granite 4.2 8B has not been scored yet and Hy-MT2-1.8B has not been scored yet.

There are no published SWE-bench Verified results for DiffusionGemma 26B A4B IT, Granite 4.2 8B 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.

DiffusionGemma 26B A4B IT has the largest context window at 262,144 tokens, against 131,072 for Granite 4.2 8B and 8,192 for Hy-MT2-1.8B. Maximum output per response: DiffusionGemma 26B A4B IT up to 32,768, Granite 4.2 8B up to 117,964, Hy-MT2-1.8B up to 4,096 tokens.

DiffusionGemma 26B A4B IT accepts text and images; Granite 4.2 8B accepts text; Hy-MT2-1.8B accepts text. DiffusionGemma 26B A4B IT handles the widest range of inputs.

Yes, all three publish their weights (Apache 2.0), so you can self-host them.

Granite 4.2 8B is the newest, released Aug 25, 2026. DiffusionGemma 26B A4B IT came out Jun 9, 2026; Hy-MT2-1.8B came out May 21, 2026. Knowledge cutoff: DiffusionGemma 26B A4B IT Jan 2025.

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.