A fast, multimodal workhorse from Google's Gemini family that handles both text and images with a notably large context window of one million tokens — meaning it can hold an enormous amount of information in a single conversation. It sits in the 'Flash' tier, suggesting it's tuned for speed and efficiency rather than maximum reasoning depth. A practical choice when you need broad context and quick turnaround over heavy deliberation.
| Benchmark | Score | Type | Recorded |
|---|---|---|---|
| LCR | 81.7 | accuracy | 29d ago |
| SWE-Bench | 80.8 | accuracy | 29d ago |
| Humanity's Last Exam | 47.9 | accuracy | 29d ago |
| LiveCodeBench | 88.7 | accuracy | 29d ago |
| SciCode | 57.2 | accuracy | 29d ago |
| GPQA Diamond | 94.5 | accuracy | 29d ago |
| MMLU-Pro | 90.1 | accuracy | 29d ago |