Model Release Radar
Price/capability frontier position, benchmark scores, and community signal
Model Release Radar
Gemma 4 12B
google·released Wednesday, Jun 3, 2026
Not enough paired price and capability data exists yet to place this model on the price/capability frontier.
This model has not been measured on DeepSWE (or any other benchmark with a real measured per-task cost) yet, so no cost/capability chart is drawn. Its Artificial Analysis benchmark scores are listed below.
Measured cost per task (DeepSWE)
This model has not been measured on DeepSWE (or any other benchmark with a real measured per-task cost) yet.
Artificial Analysis scores (no matched cost)
Artificial Analysis scores below have no measured per-task cost, so no frontier claim is made for them here.
| Benchmark | Score |
|---|---|
| AA intelligence index | 22.2 |
| AA coding index | 31.0 |
| GPQA Diamond (science) | 75.3% |
| Humanity's Last Exam | 15.7% |
| IFBench (instruction following) | 73.5% |
| LCR | 61.7% |
| SciCode (coding) | 38.2% |
| Tau2 (tool use) | 36.3% |
| Terminal-Bench (hard) | 18.2% |
| Terminal-Bench 2.1 (agentic) | 27.3% |
This page covers 2 reasoning-effort variants of the same model.
| Variant | AA coding index | AA intelligence index | Price /1M |
|---|---|---|---|
| Reasoning (shown above) | 31.0 | 22.2 | $0.15/1M |
| Non-reasoning | - | 13.2 | $0.15/1M |
No LMArena community rating is tracked for this model yet.