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 | OpenClaw Erik Steinberger | Operator OpenAI | |
|---|---|---|---|---|
| Overview | ||||
| Vendor | Nous Research | Anthropic | Erik Steinberger | OpenAI |
| Category | general | browser | general | browser |
| Release date | 2026-02-01 | — | — | — |
| Source | open source | proprietary | open source | proprietary |
| License | Apache-2.0 | — | MIT | — |
| Pricing | Free OSS | Anthropic API rates | Free OSS | ChatGPT Pro |
| Base models | ||||
| Capabilities | persistent_memoryself_improvingmulti_llmbrowser+2 | screen_controlmouse_keyboardbrowser_use | multi_llmplugin_systemmcclapersistent_state | browser_useweb_navigationform_filltask_completion |
| Capability | ||||
| gpt.buzz Index | 15.0 | 9.8 | 12.9 | 10.0 |
| SWE-bench Verified | — | — | — | — |
| SWE-bench Pro | — | — | — | — |
| Terminal-Bench 2.0 | — | — | — | — |
| GAIA | 56.0% | — | 48.0% | — |
| WebArena | — | 64.5% | — | 65.8% |
| Adoption | ||||
| OpenRouter · daily | 644B | — | 147B | — |
| OpenRouter · cumulative | 7.72T | — | 9.72T | — |
| GitHub stars | — | — | — | — |
| Links | ||||
| Links | ||||
Add an agent
Replit AgentReplit · codingmaxHermes AgentNous Research · general✓Claude CodeAnthropic · codingmaxCodexOpenAI · codingmaxCursorAnysphere · codingmaxGitHub CopilotGitHub · codingmaxClineCline · codingmaxOpenCodeOpenCode · codingmaxDevinCognition · codingmaxManusMonica · generalmaxComputer UseAnthropic · browser✓OperatorOpenAI · browser✓CometPerplexity · browsermaxv0Vercel · codingmaxBolt.newStackBlitz · codingmaxLovableLovable · codingmaxOpenClawErik Steinberger · general✓
Max 4 agents. Remove one to add another.