VerdictPal
Join

Models / Google

Gemma 4 12B (Reasoning)

Gemma · Released 2026-06-07

Google's smaller Gemma 4 reasoning variant, evaluated by Artificial Analysis on 7 Jun. Treat it as a compact open-weights reasoning candidate until the local benchmark ledger has sourced rows.

Small open-weights reasoning model for local experiments, classroom demos, and routing tests before paying for frontier APIs.

#144 of 168 on AA Index · current snapshot
22 AA Index · 9 benchmark rows · 1 sourcesPosition is benchmark-specific — not a cross-family or cross-source ranking.
Composite45
Context128K
Input / 1M—
Output / 1M—
Knowledge cutoffopen
Output speed131 t/s
TTFT (default API)1.45s
Statuslightweight

Family profile

Best published score in each covered benchmark family.

51/100 avg
Reasoning
75
Coding
38
Agentic
27
Long context
62

4 tested benchmark families

Benchmark placements

Where Gemma 4 12B (Reasoning) 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
AA output speedPerformance#24/ 187Artificial Analysis2026-09-01
IFBenchReasoning#33/ 12774Artificial Analysis2026-09-01
AA time to first tokenPerformance#47/ 186Artificial Analysis2026-09-01
AA-LCRLong context#136/ 17962Artificial Analysis2026-09-01
Humanity's Last ExamReasoning#137/ 18016Artificial Analysis2026-09-01
SciCodeCoding#142/ 18038Artificial Analysis2026-09-01
GPQA DiamondReasoning#153/ 18575Artificial Analysis2026-09-01
Terminal-BenchAgentic#158/ 18427Artificial Analysis2026-09-01
Artificial Analysis Intelligence IndexReasoning#163/ 18722Artificial Analysis2026-09-01
Family context

The three highest-scoring models with pages in each capability family. Where Gemma 4 12B (Reasoning) shows up, it's highlighted.

ReasoningGemma 4 12B (Reasoning) · 75
  1. 1
    Claude Mythos Preview
    95
  2. 2
    Gemini 3.7 Flash
    95
  3. 3
    Grok 4.6
    95
CodingGemma 4 12B (Reasoning) · 38
  1. 1
    GPT 5.5
    96
  2. 2
    Claude Opus 4.8
    96
  3. 3
    Claude Opus 4.6
    96
AgenticGemma 4 12B (Reasoning) · 27
  1. 1
    GPT 5.5
    100
  2. 2
    Claude Opus 4.8
    100
  3. 3
    Claude Fable 5
    100
Long contextGemma 4 12B (Reasoning) · 62
  1. 1
    Muse Spark 1.2
    83
  2. 2
    Kimi K3
    83
  3. 3
    Gemini 3.5 Flash
    81
Newest receipts

Benchmark rows added to the public ledger for Gemma 4 12B (Reasoning) in the last 120 days. Older rows live in the full table below.

9 recent
BenchmarkFamilyScoreSourceDays ago
AA-LCRLong context61.67%Artificial Analysis5
AA output speedPerformance131 t/sArtificial Analysis5
AA time to first tokenPerformance1.45sArtificial Analysis5
Artificial Analysis Intelligence IndexReasoning22.2%Artificial Analysis5
GPQA DiamondReasoning75.3%Artificial Analysis5
Humanity's Last ExamReasoning15.7%Artificial Analysis5
IFBenchReasoning73.54%Artificial Analysis5
SciCodeCoding38.2%Artificial Analysis5
Terminal-BenchAgentic27.34%Artificial Analysis5
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.

Reasoning75
Coding38
Agentic27
Long context62
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.

AnthropicOpenAIMistralAlibabaDeepSeekGoogleMoonshotMetaMiniMaxxAIZhipuXiaomiOtherMeituanCohereNVIDIA

Full benchmark ledger

Every catalog benchmark for Gemma 4 12B (Reasoning). Scores link to the original source; gaps mean no public row exists yet.

9 sourced rows

9 of 37 catalog benchmarks have a sourced row for Gemma 4 12B (Reasoning).

Reasoning

Coding

Agentic

Long context

Performance

Sources