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 →
| Comet Perplexity | Codex OpenAI | Devin Cognition | |
|---|---|---|---|
| Overview | |||
| Vendor | Perplexity | OpenAI | Cognition |
| Category | browser | coding | coding |
| Release date | — | — | — |
| Source | proprietary | proprietary | proprietary |
| License | — | — | — |
| Pricing | Bundled with Perplexity Pro $20/mo | Included with ChatGPT Plus/Pro | $500/mo Team |
| Base models | — | — | |
| Capabilities | browsersearchagentic | terminalfile_ioshell_execcloud_runtime | autonomouscloud_runtimemulti_sessionbrowser_use |
| Capability | |||
| gpt.buzz Index | — | 70.0 | 12.4 |
| SWE-bench Verified | — | 85.0% | 35.0% |
| SWE-bench Pro | — | 56.8% | — |
| Terminal-Bench 2.0 | — | 77.3% | — |
| GAIA | — | — | — |
| WebArena | — | — | — |
| Adoption | |||
| OpenRouter · daily | — | — | — |
| OpenRouter · cumulative | — | — | — |
| GitHub stars | — | — | — |
| Links | |||
| Links | |||
Add an agent
Replit AgentReplit · coding+Hermes AgentNous Research · general+Claude CodeAnthropic · coding+CodexOpenAI · coding✓CursorAnysphere · coding+GitHub CopilotGitHub · coding+ClineCline · coding+OpenCodeOpenCode · coding+DevinCognition · coding✓ManusMonica · general+Computer UseAnthropic · browser+OperatorOpenAI · browser+CometPerplexity · browser✓v0Vercel · coding+Bolt.newStackBlitz · coding+LovableLovable · coding+OpenClawErik Steinberger · general+