Gemma 4 12B
Gemma 4 12B is an open-weights model from Google with a 256k-token context window. No provider we track lists it yet.
Providers serving Gemma 4 12B
No provider we track lists this model yet.
Gemma 4 12B benchmark scores
Compare every model in Bench rankingsPublished scores only, each linked to its source. Ticks are every other model's best published score.
GPQA Diamond
PhD-level scientific reasoning, pass@1, no tools
thinking on 75.3%, source: Artificial Analysis, thinking onRanks 129th of 221 models with a score
MMMU-Pro (standard)
Visual reasoning, 10 answer options
thinking on 69.7%, source: Artificial Analysis, thinking onRanks 63rd of 101 models with a score
Humanity's Last Exam (text-only)
Reasoning & knowledge, no tools
thinking on 15.7%, source: Artificial Analysis, thinking onRanks 113th of 221 models with a score
τ²-Bench Telecom
Agentic tool use (telecom), with a Qwen3 model as the simulated user
thinking on 36.3%, source: Artificial Analysis, thinking onRanks 97th of 160 models with a score
Terminal-Bench 2.1 (Terminus 2)
Agentic coding & terminal use
thinking on 27.3%, source: Artificial Analysis, thinking onJoint 87th of 127 models with a score
IFBench
Instruction following, 294 prompts, 5 runs each
thinking on 73.5%, source: Artificial Analysis, thinking onRanks 27th of 158 models with a score
GDPval-AA v2.1 (Elo)
Real-world work tasks; a rating against other models, not a percentage
thinking on 427, source: Artificial Analysis, thinking onRanks 111th of 144 models with a score
Terminal-Bench Hard
Agentic coding & terminal use, Artificial Analysis's 44-task hard subset
thinking on 18.2%, source: Artificial Analysis, thinking onJoint 71st of 157 models with a score
LCR
Long-context reasoning, AA-LCR v1.1
thinking on 63.7%, source: Artificial Analysis, thinking onJoint 111th of 211 models with a score
Omni Accuracy
Omniscience knowledge accuracy
thinking on 15.6%, source: Artificial Analysis, thinking onJoint 152nd of 216 models with a score
Non-Hallucination
1 − hallucination rate
thinking off 26.6%, source: Artificial Analysis, thinking offRanks 102nd of 216 models with a score
Each score is the model's best published result across its settings, named beside it. A setting above the default can use more tokens per task, which a per-token price does not show.
Show as table
| Benchmark | Score | Setting |
|---|---|---|
GPQA Diamond PhD-level scientific reasoning, pass@1, no tools | 75.3%, source: Artificial Analysis, thinking on | thinking on |
MMMU-Pro (standard) Visual reasoning, 10 answer options | 69.7%, source: Artificial Analysis, thinking on | thinking on |
Humanity's Last Exam (text-only) Reasoning & knowledge, no tools | 15.7%, source: Artificial Analysis, thinking on | thinking on |
τ²-Bench Telecom Agentic tool use (telecom), with a Qwen3 model as the simulated user | 36.3%, source: Artificial Analysis, thinking on | thinking on |
Terminal-Bench 2.1 (Terminus 2) Agentic coding & terminal use | 27.3%, source: Artificial Analysis, thinking on | thinking on |
IFBench Instruction following, 294 prompts, 5 runs each | 73.5%, source: Artificial Analysis, thinking on | thinking on |
GDPval-AA v2.1 (Elo) Real-world work tasks; a rating against other models, not a percentage | 427, source: Artificial Analysis, thinking on | thinking on |
Terminal-Bench Hard Agentic coding & terminal use, Artificial Analysis's 44-task hard subset | 18.2%, source: Artificial Analysis, thinking on | thinking on |
LCR Long-context reasoning, AA-LCR v1.1 | 63.7%, source: Artificial Analysis, thinking on | thinking on |
Omni Accuracy Omniscience knowledge accuracy | 15.6%, source: Artificial Analysis, thinking on | thinking on |
Non-Hallucination 1 − hallucination rate | 26.6%, source: Artificial Analysis, thinking off | thinking off |
More from Google
See all 16 Google models- Gemini 2.5 Profrom $1.25 in · 1.05M · GPQA 84.4% · 3 providers
- Gemini 3.1 Flash-Litefrom $0.25 in · 1.05M · GPQA 82.2% · 3 providers
- Gemini 3.1 Pro Previewfrom $2.00 in · 1.05M · GPQA 94.1% · 3 providers
- Gemini 3.5 Flashfrom $1.50 in · 1.05M · GPQA 92.2% · 3 providers
- Gemini 3.5 Flash-Litefrom $0.30 in · 1.05M · GPQA 83.8% · 2 providers
- Gemini 3.6 Flashfrom $1.50 in · 1.05M · GPQA 92.8% · 2 providers
- Gemini 3.7 Flashfrom $0.75 in · 1.05M · GPQA 94.5% · 2 providers
- Gemini 3.8 Flashfrom $1.50 in · 1.05M · GPQA 95.3% · 2 providers
- Gemini 4 Argonfrom $4.00 in · 1.05M · GPQA 96.4% · 2 providers
- Gemini 3 Deep ThinkMMMU-Pro (standard) 81.5%
- Gemma 3 270M32k · GPQA 22.4%
- Gemma 4 26B A4B256k · GPQA 79.2%