All tasks / Tools
Gemini
Google's chat assistant on web and mobile; plan tier sets access to Flash-Lite, Flash, Pro and Gemini 4 Argon models.
- Cloud
- Free tier · from $4.99/mo
Where it ranks
- SChat & assistantsApps · Cloud · via Gemini 4 Argon
- ASearch & researchApps · Cloud · 50 on DeepResearch Bench (RACE, GPT-5.5 judge)
- SWritingApps · Cloud · via Gemini 4 Argon
- –TranslationApps · Cloud · no rated model available here yet
- –Documents & OCRApps · Cloud · no rated model available here yet
- BData analysisApps · Cloud · via Gemini 3.1 Pro (Preview)
- AImage generationApps · Cloud · via Nano Banana 2.1
- AImage editingApps · Cloud · via Nano Banana 2.1
- SImage understandingApps · Cloud · via Gemini 3.8 Flash
- AVideo generationApps · Cloud · via Gemini Omni Flash 1.1
- SVoice agentsApps · Cloud · via Gemini 3.8 Live
- AMusic generationApps · Cloud · via Lyria 3.5
- –Browser & computer agentsAgent apps & AI browsers · Cloud · no rated model available here yet
Ranked by its own benchmark result where it has one; otherwise by the best model it offers.
Facts
- Vendor
- Approach
- Apps, Agent apps & AI browsers
- Where it runs
- Cloud only: needs the vendor’s service
- Interface
- Web app, Mobile app
- Skill level
- Beginner: works out of the box
- Price
- Free tier · from $4.99/mo
- Pricing notes
- Free: Flash-Lite model; Google AI Plus $4.99/mo: Flash; Google AI Pro $19.99/mo: Pro model and Gemini 4 Argon; AI Ultra from $99.99/mo ($199.99 tier). US prices.
- Source code
- Closed source
- Last verified
- 18 Oct 2026
Price from gemini.google, 18 Oct 2026.
Models it gives you
- SGemini 4 ArgonGoogle · closed
- SGemini 3.8 LiveGoogle · closed
- SGemini 3.8 FlashGoogle · closed
- SGemini 3.1 Pro (Preview)Google · closed
- AGemini Omni Flash 1.1Google · closed
- ANano Banana 2.1Google · closed
- ALyria 3.5Google DeepMind · closed
- BNano Banana Pro (Gemini 3 Pro Image)Google · closed
Its own benchmark results
| Benchmark | Result | Entry on the leaderboard | As of | Source |
|---|---|---|---|---|
| DeepResearch Bench (RACE, GPT-5.5 judge) | 50 | gemini-2.5-pro-deepresearchRACE overall score on the maintained GPT-5.5-judge leaderboard (data_gpt55/leaderboard.csv, space last updated 2026-10-11); rank 14 of 17; comprehensiveness 50.01, insight 49.92, instruction following 50.22, readability 49.58. Gemini Deep Research run with Gemini 2.5 Pro for the 2025 DRB paper; the product now uses newer Gemini models. | 11 Oct 2026 | huggingface.co |
| DeepResearch Bench II (GPT-5.5 text-only eval) | 41.5% | Gemini 3 Pro Deep Research2025 product run (DRB2 paper), re-judged with GPT-5.5; reflects the 2025 product. | 19 Oct 2026 | huggingface.co |
| Mind2Web 2 (agentic search, private test set) | 18% | Gemini Deep ResearchMind2Web 2 paper run (mid-2025); reflects the 2025 product. | 19 Oct 2026 | osu-nlp-group.github.io |
Compare
Sources
- https://gemini.google/us/subscriptions/
- https://blog.google/products-and-platforms/products/chrome/gemini-3-auto-browse/
- https://9to5google.com/2026/01/28/chrome-gemini-auto-browse/
- https://gemini.google/gb/overview/image-generation/
- https://www.tomsguide.com/ai/ai-image-video/how-to-use-nano-banana-and-get-started-with-geminis-new-ai-image-editing-model
- https://huggingface.co/spaces/muset-ai/DeepResearch-Bench-Leaderboard
- https://blog.google/innovation-and-ai/products/gemini-app/better-tracks-lyria-gemini/
- https://ai.google.dev/gemini-api/docs/models/gemini-3.8-live
- https://osu-nlp-group.github.io/Mind2Web-2/