Compare/Agents
Compare AI agents
Pick up to 4 agents. Capability benchmarks, real-world OpenRouter usage, base models, license, and pricing render side-by-side.
Looking to compare base models instead? Switch to model compare →
| GitHub Copilot GitHub | Operator OpenAI | Devin Cognition | Computer Use Anthropic | |
|---|---|---|---|---|
| Overview | ||||
| Vendor | GitHub | OpenAI | Cognition | Anthropic |
| Category | coding | browser | coding | browser |
| Release date | — | — | — | — |
| Source | proprietary | proprietary | proprietary | proprietary |
| License | — | — | — | — |
| Pricing | Free tier · $10/mo Pro · $19/mo Business | ChatGPT Pro | $500/mo Team | Anthropic API rates |
| Base models | — | |||
| Capabilities | ideautocompletechatpr_review+1 | browser_useweb_navigationform_filltask_completion | autonomouscloud_runtimemulti_sessionbrowser_use | screen_controlmouse_keyboardbrowser_use |
| Capability | ||||
| gpt.buzz Index | — | 10.0 | 12.4 | 9.8 |
| SWE-bench Verified | — | — | 35.0% | — |
| SWE-bench Pro | — | — | — | — |
| Terminal-Bench 2.0 | — | — | — | — |
| GAIA | — | — | — | — |
| WebArena | — | 65.8% | — | 64.5% |
| Adoption | ||||
| OpenRouter · daily | — | — | — | — |
| OpenRouter · cumulative | — | — | — | — |
| GitHub stars | — | — | — | — |
| Links | ||||
| Links | ||||
Add an agent
Replit AgentReplit · codingmaxHermes AgentNous Research · generalmaxClaude CodeAnthropic · codingmaxCodexOpenAI · codingmaxCursorAnysphere · codingmaxGitHub CopilotGitHub · coding✓ClineCline · codingmaxOpenCodeOpenCode · codingmaxDevinCognition · coding✓ManusMonica · generalmaxComputer UseAnthropic · browser✓OperatorOpenAI · browser✓CometPerplexity · browsermaxv0Vercel · codingmaxBolt.newStackBlitz · codingmaxLovableLovable · codingmaxOpenClawErik Steinberger · generalmax
Max 4 agents. Remove one to add another.