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 →
| Codex OpenAI | Operator OpenAI | Claude Code Anthropic | OpenCode OpenCode | |
|---|---|---|---|---|
| Overview | ||||
| Vendor | OpenAI | OpenAI | Anthropic | OpenCode |
| Category | coding | browser | coding | coding |
| Release date | — | — | — | — |
| Source | proprietary | proprietary | proprietary | open source |
| License | — | — | — | MIT |
| Pricing | Included with ChatGPT Plus/Pro | ChatGPT Pro | Included with Claude Pro/Max/Team subscriptions | Free OSS · BYO API key |
| Base models | ||||
| Capabilities | terminalfile_ioshell_execcloud_runtime | browser_useweb_navigationform_filltask_completion | terminalfile_iomulti_file_editshell_exec+1 | terminalfile_ioshell_exec |
| Capability | ||||
| gpt.buzz Index | 70.0 | 10.0 | 95.4 | 21.9 |
| SWE-bench Verified | 85.0% | — | 80.9% | 62.0% |
| SWE-bench Pro | 56.8% | — | 55.4% | — |
| Terminal-Bench 2.0 | 77.3% | — | 65.4% | — |
| GAIA | — | — | 74.6% | — |
| WebArena | — | 65.8% | 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 · coding✓DevinCognition · codingmaxManusMonica · generalmaxComputer UseAnthropic · browsermaxOperatorOpenAI · browser✓CometPerplexity · browsermaxv0Vercel · codingmaxBolt.newStackBlitz · codingmaxLovableLovable · codingmaxOpenClawErik Steinberger · generalmax
Max 4 agents. Remove one to add another.