Updated 5 h ago · first seen 11 Sept 2026
model_01M296CE38Z87GYY5Z876B30ZK
- Context
- 256K tokens
- T2 · 5 h ago
Specification
- Openness
- open-weights
Source:Artificial AnalysisT2observed 5 h agomedium
- Context window
- 256K tokens
Source:Artificial AnalysisT2observed 5 h agomedium
- Hugging Face repo
- google/gemma-4-12B
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 7 h agomedium
- Aa median output tokens per second
- 106.9
Source:Artificial AnalysisT2observed 5 h agomedium
Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →
Provenance
Attributed facts
5
Source tiers
T25
Freshest observation
5 h ago
Conflicts
None
Modalities
Modalities unavailable.
Capabilities
Tool calling
Unavailable
Structured output
Unavailable
Reasoning
Yes
Artificial Analysis · T2
Vision
Unavailable
Audio
Unavailable
Fine-tuning available
Unavailable
- Context window
- 256K tokens
Source:Artificial AnalysisT2observed 5 h agomedium
| Benchmark | Score | Metric | Config | Evaluated | Source |
|---|---|---|---|---|---|
| τ²-bench | 36.26% | pass^1 | aa_slug=gemma-4-12b · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
| Artificial Analysis Intelligence Index | 14.18 | index | aa_slug=gemma-4-12b · version=4.3 · estimated=true | — | artificialanalysis.aiT2 |
| GPQA | 75.25% | accuracy | aa_slug=gemma-4-12b · variant=GPQA Diamond · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
| Humanity's Last Exam | 15.66% | accuracy | aa_slug=gemma-4-12b · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
| IFBench | 73.54% | accuracy | aa_slug=gemma-4-12b · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
| MMMU-Pro | 69.65% | accuracy | aa_slug=gemma-4-12b · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
| Terminal-Bench | 27.34% | accuracy | aa_slug=gemma-4-12b · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
| Terminal-Bench | 18.18% | accuracy | aa_slug=gemma-4-12b · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
Scores are reported as published, with their evaluation configuration (harness, prompting, judge). Results with different configs are not directly comparable — see methodology.
Current prices
No current prices recorded
Price history
No hardware estimate available
Ancestors 0
None recorded.
This model
gemma-4-12B
Quantizations 0
None recorded.
Descendants 1
Papers 0
No papers linked yet.
Repositories 0
No repositories linked yet.
As of
Rewind the record: see this entity's attributes exactly as AI Atlas knew them on a given day.
Claim history · Aa median output tokens per second
Aa median output tokens per secondmetric.aa_median_output_tokens_per_second1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| 106.9 | → current | current | Artificial AnalysisT2 | medium | deterministic |
Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →
gemma-4-12B scores 18.18% on Terminal-Bench
artificial_analysisgemma-4-12B scores 27.34% on Terminal-Bench
artificial_analysisgemma-4-12B scores 15.66% on Humanity's Last Exam
artificial_analysisgemma-4-12B scores 14.18 on Artificial Analysis Intelligence Index
artificial_analysis
| Source | Document | Type | Tier | Last observed | Snapshots |
|---|---|---|---|---|---|
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/google/gemma-4-12B-it | model_page | T2· Quality secondary | 2 h ago | 3 |
| Artificial Analysis | artificialanalysis.ai/leaderboards/models | leaderboard | T2· Quality secondary | 5 h ago | 1 |
Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.