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 →
| Hermes Agent Nous Research | Computer Use Anthropic | Codex OpenAI | Lovable Lovable | |
|---|---|---|---|---|
| Overview | ||||
| Vendor | Nous Research | Anthropic | OpenAI | Lovable |
| Category | general | browser | coding | coding |
| Release date | 2026-02-01 | — | — | — |
| Source | open source | proprietary | proprietary | proprietary |
| License | Apache-2.0 | — | — | — |
| Pricing | Free OSS | Anthropic API rates | Included with ChatGPT Plus/Pro | $20/mo Pro |
| Base models | — | |||
| Capabilities | persistent_memoryself_improvingmulti_llmbrowser+2 | screen_controlmouse_keyboardbrowser_use | terminalfile_ioshell_execcloud_runtime | full_stackapp_generationauthdatabase |
| Capability | ||||
| gpt.buzz Index | 15.0 | 9.8 | 70.0 | — |
| SWE-bench Verified | — | — | 85.0% | — |
| SWE-bench Pro | — | — | 56.8% | — |
| Terminal-Bench 2.0 | — | — | 77.3% | — |
| GAIA | 56.0% | — | — | — |
| WebArena | — | 64.5% | — | — |
| Adoption | ||||
| OpenRouter · daily | 644B | — | — | — |
| OpenRouter · cumulative | 7.72T | — | — | — |
| GitHub stars | — | — | — | — |
| Links | ||||
| Links | ||||
Add an agent
Replit AgentReplit · codingmaxHermes AgentNous Research · general✓Claude CodeAnthropic · codingmaxCodexOpenAI · coding✓CursorAnysphere · codingmaxGitHub CopilotGitHub · codingmaxClineCline · codingmaxOpenCodeOpenCode · codingmaxDevinCognition · codingmaxManusMonica · generalmaxComputer UseAnthropic · browser✓OperatorOpenAI · browsermaxCometPerplexity · browsermaxv0Vercel · codingmaxBolt.newStackBlitz · codingmaxLovableLovable · coding✓OpenClawErik Steinberger · generalmax
Max 4 agents. Remove one to add another.