What are DiffusionGemma 26B A4B's benchmark scores?

As of 25 Oct 2026, DiffusionGemma 26B A4B scores 45.4 ±7.2 on the BenchLeader Index, strongest in instruction following (60) and weakest in long context (34). That rests on 6 independent benchmark results, and every score on this page links to its publisher.

How does DiffusionGemma 26B A4B rank?

DiffusionGemma 26B A4B is #515 of 785 ranked configurations on 25 Oct 2026. 412 other configurations score within its margin, so the exact position matters less than the band. The leader is Claude Opus 5.5 (max effort) at 72.6.

When was DiffusionGemma 26B A4B released?

Google released DiffusionGemma 26B A4B on 10 Jun 2026.

GoogleOpen weightsReasoning modelCompare with another model

DiffusionGemma 26B A4B

DiffusionGemma 26B A4B is a Google open-weights reasoning model, released 10 Jun 2026. Its best configuration ranks #515 of 785 on the BenchLeader Index at 45.4 ±7.2, in the lower half. The ± is the point: 412 other configurations score within that range, so they and this one cannot be told apart on quality alone — price and speed are what separate them. It scores highest in instruction following (60) and lowest in long context (34). Last measured 10 Jun 2026.

Blended price: –
Output speed: –
First answer: –
Context: 256k
Full answer: –
Cost per run: –
Released: 10 Jun 2026

How it scores by categoryDashed line = average model (50). One step of 15 = one standard deviation.

Overall index45
Reasoning41
Knowledge35
Instruction following60
Multimodal49
Long context34
Composite40

How its index has moved

9 Sept 2026 to 21 Oct 2026

The index is recomputed from scratch every day, so a line moves when a new benchmark result lands, when a publisher revises a score, or when the models it is normalised against change. Early movement usually means the score is still settling.

Benchmark results

See all LLM benchmarks. One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.

Reasoning

Benchmark	not stated	Source
GPQA Diamond (AA)not in index	66.9%#327	Artificial Analysis
Humanity's Last Exam (AA)not in index	10.8%#309	Artificial Analysis
CritPt	0.3%#271	Artificial Analysis

Coding

Benchmark	not stated	Source	Trend
Terminal-Bench 2.1 (AA)not in index	12.4%#188	Artificial Analysis

Agents & tools

Benchmark	not stated	Source	Trend
GDPval-AA v2.1not in index	0.0%#124	Artificial Analysis

Knowledge

Benchmark	not stated	Source
AA-Omniscience	-59.2#460	Artificial Analysis
AA-Omniscience: accuracynot in index	16.6%#386	Artificial Analysis
AA-Omniscience: non-hallucinationnot in index	9.1%#436	Artificial Analysis

Instruction following

Benchmark	not stated	Source	Trend
IFBench	59.5%#129	Artificial Analysis

Multimodal

Benchmark	not stated	Source	Trend
MMMU-Pro	66.5%#171	Artificial Analysis

Long context

Benchmark	not stated	Source	Trend
AA-LCR	19.7%#437	Artificial Analysis

Composite

Benchmark	not stated	Source	Trend
AA Intelligence Index v4.3.2	9.5#396	Artificial Analysis

New this month

Questions people ask

What are DiffusionGemma 26B A4B's benchmark scores?: As of 25 Oct 2026, DiffusionGemma 26B A4B scores 45.4 ±7.2 on the BenchLeader Index, strongest in instruction following (60) and weakest in long context (34). That rests on 6 independent benchmark results, and every score on this page links to its publisher.
How does DiffusionGemma 26B A4B rank?: DiffusionGemma 26B A4B is #515 of 785 ranked configurations on 25 Oct 2026. 412 other configurations score within its margin, so the exact position matters less than the band. The leader is Claude Opus 5.5 (max effort) at 72.6.
When was DiffusionGemma 26B A4B released?: Google released DiffusionGemma 26B A4B on 10 Jun 2026.

Data as of 25 Oct 2026. Compare with another model.

Cite as: BenchLeader, “DiffusionGemma 26B A4B: benchmarks, pricing, speed and rank”, data as of 25 Oct 2026, https://www.benchleader.com/models/diffusiongemma-26b-a4b.