Model Release Radar
Price/capability frontier position, benchmark scores, and community signal
Model Release Radar
Gemini 3 Flash Preview
google·closed weights·Proprietary·released Wednesday, Dec 17, 2025
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 | 27.9 |
| AIME 2025 (math) | 55.7% |
| GPQA Diamond (science) | 81.2% |
| Humanity's Last Exam | 15.0% |
| IFBench (instruction following) | 55.1% |
| LCR | 53.0% |
| LiveCodeBench (coding) | 79.7% |
| MMLU-Pro (knowledge) | 88.2% |
| SciCode (coding) | 49.9% |
| Tau2 (tool use) | 43.3% |
| Terminal-Bench (hard) | 31.8% |
This page covers 2 reasoning-effort variants of the same model.
| Variant | AA coding index | AA intelligence index | Price /1M |
|---|---|---|---|
| Standard (shown above) | - | 27.9 | $1.12/1M |
| Thinking (minimal) | - | - | undisclosed |
| Variant | Coding Elo | Overall Elo | Votes |
|---|---|---|---|
| Standard | 1,462 | 1,467 | 30,242 |
| Thinking (minimal) | 1,437 | 1,442 | 85,940 |