GPQA DiamondVerified
75.3%
GPQA Diamond (AA run)
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.
Composite45
Context128K
Input / 1M—
Output / 1M—
Knowledge cutoffopen
Output speed111 t/s
Statuslightweight
Family profile
Best published score in each covered benchmark family.
55/100 avg
- Reasoning
- 75
- Agentic
- 27
- Long context
- 64
3 tested benchmark families
Benchmark placements
Per-benchmark positions
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.
| Benchmark | Family | Rank | Score | Source | Date |
|---|---|---|---|---|---|
| AA output speed | Performance | #53/ 195 | Artificial Analysis | 2026-10-12 | |
| Terminal-Bench | Agentic | #141/ 167 | 27 | Artificial Analysis | 2026-09-28 |
| Humanity's Last Exam | Reasoning | #144/ 186 | 16 | Artificial Analysis | 2026-09-28 |
| AA-LCR | Long context | #148/ 184 | 64 | Artificial Analysis | 2026-09-28 |
| GPQA Diamond | Reasoning | #153/ 184 | 75 | Artificial Analysis | 2026-09-28 |
Family context
Strongest rows in each family
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
- 196
- 295
- 395
Math
- 152
- 252
- 350
AgenticGemma 4 12B (Reasoning) · 27
- 191
- 289
- 389
Long contextGemma 4 12B (Reasoning) · 64
- 189
- 286
- 385
Newest receipts
5 recentLast 120 days
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.
| Benchmark | Family | Score | Source | Days ago |
|---|---|---|---|---|
| AA output speed | Performance | 111 t/s | Artificial Analysis | 10 |
| AA-LCR | Long context | 63.67% | Artificial Analysis | 24 |
| GPQA Diamond | Reasoning | 75.3% | Artificial Analysis | 24 |
| Humanity's Last Exam | Reasoning | 15.7% | Artificial Analysis | 24 |
| Terminal-Bench | Agentic | 27.34% | Artificial Analysis | 24 |
Family coverage
Best score per family
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.
Price vs. performance
Where Gemma 4 12B (Reasoning) sits on the scatter
Hover any dot for name, score, and input price. Keyboard: tab through the top twelve, or use the ranking below.
AnthropicOpenAIGoogleAlibabaMetaZhipuxAIDeepSeekMiniMaxXiaomiMoonshotOtherMeituanMistralNVIDIACohere
Full benchmark ledger
Every catalog benchmark for Gemma 4 12B (Reasoning). Scores link to the original source; gaps mean no public row exists yet.
5 of 13 catalog benchmarks have a sourced row for Gemma 4 12B (Reasoning).
Reasoning
Humanity's Last ExamVerified
15.7%
HLE (AA run)
Agentic
Terminal-BenchVerified
27.34%
Terminal-Bench v2.1 (AA run)
Long context
AA-LCRVerified
63.67%
AA-LCR (AA run)
Performance
AA output speedVerified
111 t/s
Median output tokens/s (1k prompt, default provider)
Sources
Where the numbers come from
- Gemma docs· checked 2026-06-14
- Artificial Analysis models index· checked 2026-06-14
Questions this model page answers
Every answer below is assembled from the dated fields on this page. Nothing is written separately for search.
What is Gemma 4 12B (Reasoning)?
Gemma 4 12B (Reasoning) is a Google model: 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.
What is Gemma 4 12B (Reasoning) for?
Small open-weights reasoning model for local experiments, classroom demos, and routing tests before paying for frontier APIs.
What does Gemma 4 12B (Reasoning) cost?
Gemma 4 12B (Reasoning) lists — input and — output per 1M tokens. Pricing last checked 2026-06-14.
How large is the Gemma 4 12B (Reasoning) context window?
Gemma 4 12B (Reasoning) publishes a 128K token context window.
What is the VerdictPal status of Gemma 4 12B (Reasoning)?
Gemma 4 12B (Reasoning) carries Lightweight status on the model atlas.
The Pack · Editorial newsletter
Know when the rules move.
One short email when a university changes its AI rule for theses, or a research tool changes its pricing or privacy terms. No tracking, no third-party analytics. Unsubscribe in one click.