All tasks / Models
Gemini 3.8 Flash
Google's Flash tier of faster, lower-cost Gemini models, aimed at agents, coding and high-volume use.
- Closed
- Released 2 Sep 2026
Where it ranks
- SChat & assistantsModels · Cloud · 1,496 on LMArena Text Arena (overall, style control)
- –Search & researchModels · Cloud · no result on this task’s benchmarks yet
- SWritingModels · Cloud · 1,487 on LMArena Text Arena: Creative Writing (style control)
- –Documents & OCRModels · Cloud · no result on this task’s benchmarks yet
- CCodingModels · Cloud · 1,586 on LMArena WebDev / Code Arena (overall)
- SImage understandingModels · Cloud · 1,289 on LMArena Vision Arena (overall, style control)
- CVector graphics & logosModels · Cloud · 1,294 on Design Arena SVG
- –Browser & computer agentsModels · Cloud · no result on this task’s benchmarks yet
- BWorkflow automationModels · Cloud · 59.9% on AutomationBench-AA (Artificial Analysis)
- BSlides & presentationsModels · Cloud · 1,179 on Design Arena Python-PPTX Slides
Facts
- Vendor
- Family
- Gemini Flash
- Released
- 2 Sep 2026
- Weights
- Closed: API and apps only
- License
- proprietary
- API price
- $0.75 in / $3.75 out per 1M tokens
- Access
- Free tier available
- Last verified
- 18 Oct 2026
Price from ai.google.dev, 18 Oct 2026.
Benchmark results
| Benchmark | Result | Entry on the leaderboard | As of | Source |
|---|---|---|---|---|
| Artificial Analysis Intelligence Index | 41 | Gemini 3.8 Flash (High)Raw value from the page's embedded model data; the site displays it rounded to an integer. | 18 Oct 2026 | artificialanalysis.ai |
| Artificial Analysis MMMU-Pro (independent evaluation) | 85.6% | Gemini 3.8 Flash (High)Raw fraction 0.8561 from the model data embedded in https://artificialanalysis.ai/leaderboards/models, converted to percent; rank 9 of 124 entries with an MMMU-Pro result; no last-updated date shown. | 19 Oct 2026 | artificialanalysis.ai |
| AutomationBench-AA (Artificial Analysis) | 59.9% | Gemini 3.8 Flash (High)AutomationBench-AA Score (share of each task's objectives completed, a task with any guardrail violation scoring zero); raw value from the page's embedded model data (displayed rounded); rank 18 of 32; Tasks Completed 32.12%, Objectives Completed 75.66%; no last-updated date shown, so as_of = retrieval date. | 19 Oct 2026 | artificialanalysis.ai |
| Design Arena Python-PPTX Slides | 1,179 | Gemini 3.8 Flash815 battles. Read from the site's own API (page renders client-side). | 18 Oct 2026 | designarena.ai |
| Design Arena SVG | 1,294 | Gemini 3.8 FlashDesign Arena SVG, rank 14, 2209 battles; rows read from POST https://www.designarena.ai/api/leaderboard (arenaType 'models', category 'svg'); names from https://www.designarena.ai/api/registry | 19 Oct 2026 | designarena.ai |
| EQ-Bench Creative Writing v3 | 1,748 | gemini-3.8-flashElo score from the leaderboard data embedded in https://eqbench.com/creative_writing.js (file last modified 2026-09-24); rank 30 of 140; rubric score 16.54. Marked as a new entry on the board. | 24 Sep 2026 | eqbench.com |
| LMArena Text Arena (overall, style control) | 1,496 | Gemini 3.8 Flash (High)From LMArena's official leaderboard-dataset (text_style_control, split latest, category overall, published 2026-10-15), which mirrors https://arena.ai/leaderboard/text (site blocks automated fetches). | 15 Oct 2026 | huggingface.co |
| LMArena Text Arena: Creative Writing (style control) | 1,487 | Gemini 3.8 Flash (High)From LMArena's official leaderboard-dataset (text_style_control, split latest, category creative_writing, published 2026-10-15), which mirrors https://arena.ai/leaderboard/text/creative-writing (site blocks automated fetches). Rank 7 of 414; 8232 votes; 95% CI 1479.0-1494.9. | 15 Oct 2026 | huggingface.co |
| LMArena Vision Arena (overall, style control) | 1,289 | gemini-3.8-flash-highFrom LMArena's official leaderboard-dataset (vision_style_control, split latest, category overall, published 2026-10-09), which mirrors https://arena.ai/leaderboard/vision (site blocks automated fetches). Rank 14 of 165; 3792 votes; 95% CI 1278.5-1299.7. | 9 Oct 2026 | huggingface.co |
| LMArena WebDev / Code Arena (overall) | 1,586 | Gemini 3.8 Flash (High)From LMArena's official leaderboard-dataset (webdev = Code Arena, split latest, category overall, published 2026-10-18), which mirrors https://arena.ai/leaderboard/webdev. Rank 33; 10730 votes; 95% CI 1578.3-1593.1. | 18 Oct 2026 | huggingface.co |
| ParseBench (models) | 72.1% | Google Gemini 3.8 Flash (Thinking High)Overall (mean of tables, charts, content faithfulness, semantic formatting, visual grounding) from leaderboard.csv in the ParseBench repo (last leaderboard commit 2026-10-09). Best of three thinking levels. | 9 Oct 2026 | github.com |
| SWE-Bench Pro V2 (public set, full) | 94.9% | Gemini 3.8 Flash (mini-swe-agent) highSWE-Bench Pro V2 Full (642 tasks); row added 2026-10-07; 95% CI +/-1.46; harness in the variant name; read from the leaderboard page's embedded data. | 19 Oct 2026 | labs.scale.com |
Where you can use it
- SAbacus AI DesktopCoding agents · Cloud
- SBase44App builders · Cloud
- SBlinkApp builders · Cloud
- SCapyCoding agents · Cloud
- SCursorEditors & extensions · Cloud
- SGeminiApps · Cloud
- CGemini CLICoding agents · Cloud
- SGemini Enterprise Agent Platform (formerly Vertex AI)Runtimes & gateways · Cloud
- SGitHub CopilotEditors & extensions · Cloud
- SGoogle AI StudioApps · Cloud
- AGoogle AntigravityEditors & extensions · Cloud
- AJetBrains AirEditors & extensions · Cloud
- SLiteLLMRuntimes & gateways · Local
- ALLM (CLI)Runtimes & gateways · Local
- SMammouthApps · Cloud
- –mini-swe-agentCoding agents · Local
- –NanocoderCoding agents · Local
- SOpenRouterRuntimes & gateways · Cloud
- SPerplexityApps · Cloud
- SPoeApps · Cloud
- SPortkey AI GatewayRuntimes & gateways · Local
- SRequestyRuntimes & gateways · Cloud
- STRAEEditors & extensions · Cloud
- ATypingMindApps · Local
- SVeniceApps · Cloud
- SVercel AI GatewayRuntimes & gateways · Cloud
- –ZedEditors & extensions · Local
Earlier versions
- Gemini 3.7 Flash · 13 Aug 2026
- Gemini 3.6 Flash · 21 Jul 2026
- Gemini 3.5 Flash · 19 May 2026
Compare
Sources
- https://ai.google.dev/gemini-api/docs/models
- https://ai.google.dev/gemini-api/docs/changelog
- https://ai.google.dev/gemini-api/docs/pricing
- https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset
- https://artificialanalysis.ai/leaderboards/models
- https://www.tbench.ai/
- https://ai.google.dev/gemini-api/docs/computer-use
- https://arena.ai/leaderboard/vision
- https://arena.ai/leaderboard/text/creative-writing
- https://eqbench.com/creative_writing.html
- https://www.designarena.ai/leaderboard/agentic-slides
- https://github.com/run-llama/ParseBench
- https://artificialanalysis.ai/evaluations/mmmu-pro
- https://labs.scale.com/leaderboard/swe_bench_pro_public_v2
- https://www.designarena.ai/leaderboard/svgs
- https://artificialanalysis.ai/evaluations/automationbench-aa