ChatGPT

OpenAI's chat assistant on web, desktop and mobile, built on its GPT model family.

Where it ranks

S
Chat & assistants
Apps · Cloud · via GPT-6.1 Sol
A
Search & research
Apps · Cloud · 48 on DeepResearch Bench (RACE, GPT-5.5 judge)
A
Writing
Apps · Cloud · via GPT-6.1 Sol
–
Translation
Apps · Cloud · no rated model available here yet
–
Documents & OCR
Apps · Cloud · no rated model available here yet
C
Data analysis
Apps · Cloud · 45.5% on SpreadsheetBench (V1 full, 912 tasks)
S
Image generation
Apps · Cloud · via GPT Image 2.5
S
Image editing
Apps · Cloud · via GPT Image 2.5
S
Image understanding
Apps · Cloud · via GPT-6.1 Sol
A
Voice agents
Apps · Cloud · via GPT-Live 1
–
Browser & computer agents
Agent apps & AI browsers · Cloud · no rated model available here yet
A
Workflow automation
Agent builders · Cloud · via GPT-6 Astra
A
Slides & presentations
Apps · Cloud · via GPT-6 Astra

Ranked by its own benchmark result where it has one; otherwise by the best model it offers.

Vendor: OpenAI
Approach: Apps, Agent apps & AI browsers, Agent builders
Where it runs: Cloud only: needs the vendor’s service
Interface: Web app, Desktop app, Mobile app
Skill level: Beginner: works out of the box
Price: Free tier · from $20/mo
Pricing notes: Free and Go ($8/mo) are limited to the small Luna model; Plus ($20/mo) adds the larger GPT-6-generation models; Pro from $100/mo ($100/$200/$500 tiers); Business $20/user/mo annual ($25 monthly).
Source code: Closed source
Last verified: 18 Oct 2026

Price from learn.chatgpt.com, 18 Oct 2026.

Benchmark	Result	Entry on the leaderboard	As of	Source
DeepResearch Bench (RACE, GPT-5.5 judge)	48	`openai-deepresearch` RACE overall score on the maintained GPT-5.5-judge leaderboard (data_gpt55/leaderboard.csv, space last updated 2026-10-11); rank 15 of 17; comprehensiveness 48.05, insight 46.69, instruction following 49.29, readability 47.62. OpenAI deep research (ChatGPT) as run for the 2025 DRB paper; the product now uses newer models.	11 Oct 2026	huggingface.co
DeepResearch Bench II (GPT-5.5 text-only eval)	43.1%	`GPT-o3 Deep Research` 2025 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)	28%	`OpenAI Deep Research` Mind2Web 2 paper run (mid-2025); reflects the 2025 product.	19 Oct 2026	osu-nlp-group.github.io
SpreadsheetBench (V1 full, 912 tasks)	45.5%	`ChatGPT Agent w/ .xlsx` SpreadsheetBench V1 Full (912); entry date 2025-07-17; not verified (reported by OpenAI). Also listed: 'ChatGPT Agent' 35.3.	18 Oct 2026	spreadsheetbench.github.io