Gemini 3 Flash
Google·
LLMsmidcloud
Overview
Flash-tier model offering frontier-level reasoning at lower cost and higher speed. Predecessor to Gemini 3.5 Flash.
Capabilities and innovations
High-speed reasoningMultimodal input
Benchmarks
| Benchmark | Score | Source |
|---|---|---|
| GPQA Diamond | 90.4% | vendor |
| Humanity’s Last Exam (no tools) | 33.7% | vendor |
| SWE-bench Verified | 78% | unsourced |
| MMLU-Pro | 88.59% | unsourced |
| MMMU-Pro | 81.2% | vendor |
- SWE-bench Pro: not reported by the vendor
- Terminal-Bench 2.x: benchmark did not exist at release
API pricing
$0.5 per million input tokens, $3 per million output tokens (USD, cheapest OpenRouter endpoint, checked 2026-06-08)
Links
More from Google
Data curated by AI Model Timeline. See the methodology for admission criteria, benchmark eras and source priority.