Gemini 3.5 Flash
Google·
Overview
Fast-tier model in the Gemini 3.5 generation, announced at Google I/O 2026. GA at launch and set as the default model in the Gemini app and AI Mode in Google Search. Architecture is not publicly disclosed. Vendor-reported benchmarks: GPQA Diamond 90.4, MMMU-Pro 81.2, SWE-bench Verified 78. Independent (Artificial Analysis, ~5 days post-launch): HLE 40.2 (exact match to vendor figure), Terminal-Bench 2.1 76.2, AA Intelligence Index v4.0: 55. Distinct from 'Gemini Omni', a separate video/world model announced at the same event.
Capabilities and innovations
Benchmarks
| Benchmark | Score | Source |
|---|---|---|
| GPQA Diamond | 90.4% | vendor GPQA Diamond 90.4. |
| Humanity’s Last Exam (no tools) | 40.2% | independent HLE 40.2 — Artificial Analysis, ~5 days post-launch. Exact match to Google's own figure (delta = 0). Confirmed as a component of Intelligence Index v4.0. |
| SWE-bench Verified | 78% | vendor SWE-bench Verified 78. |
| MMLU-Pro | 89.52% | unsourced |
| Terminal-Bench 2.x | 76.2% | independent Terminal-Bench 2.1 76.2 — Artificial Analysis. Note: this is Terminal-Bench 2.1, not the older 2.0. |
| MMMU-Pro | 81.2% | vendor MMMU-Pro 81.2 (vendor). Note: llm-stats reports 83.6 in an independent run; tracked discrepancy. |
- SWE-bench Pro: not reported by the vendor
- MMLU: not reported by the vendor
API pricing
$1.5 per million input tokens, $9 per million output tokens (USD, cheapest OpenRouter endpoint, checked 2026-05-21)
Links
More from Google
Data curated by AI Model Timeline. See the methodology for admission criteria, benchmark eras and source priority.