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 →
| Claude Code Anthropic | Manus Monica | Devin Cognition | Codex OpenAI | |
|---|---|---|---|---|
| Overview | ||||
| Vendor | Anthropic | Monica | Cognition | OpenAI |
| Category | coding | general | coding | coding |
| Release date | — | — | — | — |
| Source | proprietary | proprietary | proprietary | proprietary |
| License | — | — | — | — |
| Pricing | Included with Claude Pro/Max/Team subscriptions | Subscription tiers | $500/mo Team | Included with ChatGPT Plus/Pro |
| Base models | — | — | ||
| Capabilities | terminalfile_iomulti_file_editshell_exec+1 | browser_usefile_iomulti_agentautonomous | autonomouscloud_runtimemulti_sessionbrowser_use | terminalfile_ioshell_execcloud_runtime |
| Capability | ||||
| gpt.buzz Index | 95.4 | 13.7 | 12.4 | 70.0 |
| SWE-bench Verified | 80.9% | — | 35.0% | 85.0% |
| SWE-bench Pro | 55.4% | — | — | 56.8% |
| Terminal-Bench 2.0 | 65.4% | — | — | 77.3% |
| GAIA | 74.6% | 51.0% | — | — |
| WebArena | 64.5% | — | — | — |
| Adoption | ||||
| OpenRouter · daily | 73.5B | — | — | — |
| OpenRouter · cumulative | 3.52T | — | — | — |
| GitHub stars | — | — | — | — |
| Links | ||||
| Links | ||||
Add an agent
Replit AgentReplit · codingmaxHermes AgentNous Research · generalmaxClaude CodeAnthropic · coding✓CodexOpenAI · coding✓CursorAnysphere · codingmaxGitHub CopilotGitHub · codingmaxClineCline · codingmaxOpenCodeOpenCode · codingmaxDevinCognition · coding✓ManusMonica · general✓Computer UseAnthropic · browsermaxOperatorOpenAI · browsermaxCometPerplexity · browsermaxv0Vercel · codingmaxBolt.newStackBlitz · codingmaxLovableLovable · codingmaxOpenClawErik Steinberger · generalmax
Max 4 agents. Remove one to add another.