VerdictPal
Join

Models / Google

DiffusionGemma 26B A4B

DiffusionGemma 26B · Released 2026-06-10

AA Intelligence Index 13.5. Listed on Artificial Analysis with API pricing $0/$0 per 1M tokens. Benchmark rows sync from the AA snapshot — see the ledger on this page.

Frontier model tracked on Artificial Analysis. Use the benchmark ledger below for sourced scores; we do not infer numbers beyond published rows.

#169 of 184 on AA Index · current snapshot
10 AA Index · 8 benchmark rows · 1 sourcesPosition is benchmark-specific — not a cross-family or cross-source ranking.
Composite31
ContextUnlisted
Input / 1MFree
Output / 1MFree
Knowledge cutoffunpublished
Statussolid

Family profile

Best published score in each covered benchmark family.

33/100 avg
Reasoning
67
Agentic
12
Long context
20

3 tested benchmark families

Benchmark placements

Where DiffusionGemma 26B A4B places on each public benchmark source that publishes a row. Rank counts every model with a latest row in the same test — not a universal quality score.

BenchmarkFamilyRankScoreSourceDate
IFBenchReasoning#80/ 12759Artificial Analysis2026-09-10
AA output speedPerformance#106/ 190Artificial Analysis2026-09-10
AA time to first tokenPerformance#106/ 190Artificial Analysis2026-09-10
Humanity's Last ExamReasoning#156/ 18511Artificial Analysis2026-09-10
GPQA DiamondReasoning#173/ 19067Artificial Analysis2026-09-10
Artificial Analysis Intelligence IndexReasoning#175/ 18810Artificial Analysis2026-09-10
AA-LCRLong context#177/ 18220Artificial Analysis2026-09-10
Terminal-BenchAgentic#177/ 18912Artificial Analysis2026-09-10
Family context

The three highest-scoring models with pages in each capability family. Where DiffusionGemma 26B A4B shows up, it's highlighted.

ReasoningDiffusionGemma 26B A4B · 67
  1. 1
    GPT-6 Astra
    96
  2. 2
    Claude Mythos Preview
    95
  3. 3
    Gemini 3.7 Flash
    95
AgenticDiffusionGemma 26B A4B · 12
  1. 1
    GPT 5.5
    100
  2. 2
    Claude Opus 4.8
    100
  3. 3
    Claude Fable 5
    100
Long contextDiffusionGemma 26B A4B · 20
  1. 1
    Kimi K3
    89
  2. 2
    Claude Fable 5.1
    85
  3. 3
    GPT-5.5 (high)
    84
Newest receipts

Benchmark rows added to the public ledger for DiffusionGemma 26B A4B in the last 120 days. Older rows live in the full table below.

8 recent
BenchmarkFamilyScoreSourceDays ago
AA-LCRLong context19.67%Artificial Analysis4
AA output speedPerformance0 t/sArtificial Analysis4
AA time to first tokenPerformance0.00sArtificial Analysis4
Artificial Analysis Intelligence IndexReasoning9.5%Artificial Analysis4
GPQA DiamondReasoning66.9%Artificial Analysis4
Humanity's Last ExamReasoning10.8%Artificial Analysis4
IFBenchReasoning59.46%Artificial Analysis4
Terminal-BenchAgentic12.36%Artificial Analysis4
Family coverage

A high composite that hides a weak family is a trap. These bars surface the families where this model hasn't been publicly tested, and where it leads.

Reasoning67
Agentic12
Long context20
Price vs. performance
0255075100$0.10$0.30$1$3$10$30input USD / 1M tokens · log scale →← intelligence

Hover any dot for name, score, and input price. Keyboard: tab through the top twelve, or use the ranking below.

AnthropicOpenAIMistralAlibabaDeepSeekGoogleMoonshotMetaxAIMiniMaxZhipuXiaomiOtherMeituanCohereNVIDIA

Full benchmark ledger

Every catalog benchmark for DiffusionGemma 26B A4B. Scores link to the original source; gaps mean no public row exists yet.

8 sourced rows

8 of 37 catalog benchmarks have a sourced row for DiffusionGemma 26B A4B.

Reasoning

Agentic

Long context

Performance

Sources