Autonomous Coding Agents Leaderboard
Standardized SWE-bench Verified evaluations, multi-file codebase navigation, terminal execution access, and unit cost per solved task as of September 2026.
Verified Developer Telemetry 2026Showing 18 of 18 agents & IDEs
| Rank | Autonomous Agent / AI IDE | Underlying Model | Index | SWE-bench Verified | Terminal-Bench | Avg Cost / Task | Pricing Tier | Action |
|---|---|---|---|---|---|---|---|---|
| #1 | Cursorby Anysphere • AI-First IDEThe AI-first code editor built for blazing-fast multi-file engineering and predictive completions. | Claude 3.7 Sonnet / DeepSeek-V3 | 78.8 | 69.2% | 66.2% | $0.68 | FreemiumFree tier with 2,000 completions | Details |
| #2 | Windsurfby Codeium • AI-First IDEThe next-generation agentic IDE featuring Cascade bidirectional flow between editor and terminal. | Claude 3.7 Sonnet / Cascade Flow | 76.5 | 68.0% | 64.5% | $0.55 | FreemiumFree tier with unlimited autocomplete | Details |
| #3 | Claude Codeby Anthropic • Autonomous CLI AgentAnthropic's high-agency CLI agent that navigates repositories, runs terminals, and commits verified PRs. | Claude 3.7 Sonnet (Hybrid Reasoning) | 82.5 | 72.8% | 68.5% | $0.85 | PaidPay-as-you-go via Anthropic API (Claude 3.7 Sonnet tokens). Built-in prompt caching reduces cost by up to 90%. | Details |
| #4 | Devinby Cognition AI • Autonomous Cloud AgentThe world's first fully autonomous AI software engineer, operating in an isolated cloud VM. | Cognition Proprietary Ensemble (Claude 3.7 + o3-mini) | 76.8 | 70.4% | 65.8% | $1.40 | PaidTeam plan starts at $500/month (includes dedicated compute hours) | Details |
| #5 | GitHub Copilotby GitHub & Microsoft • In-IDE ExtensionThe world's most widely adopted AI developer tool, deeply embedded across Microsoft's development ecosystem. | GPT-4o / Claude 3.5 Sonnet / o3-mini | 74.2 | 65.0% | 62.0% | $0.75 | FreemiumFree tier with 2,000 completions/month | Details |
| #6 | Clineby Cline Community • In-IDE ExtensionThe leading open-source autonomous coding agent for VS Code with human-in-the-loop permission controls. | Claude 3.7 Sonnet / DeepSeek-R1 | 75.2 | 66.8% | 63.8% | $0.42 | Open Source100% Free & Open Source (Apache 2.0). Pay model providers directly via API key (BYOK). | Details |
| #7 | Roo Codeby Roo Vet & Community • In-IDE ExtensionAdvanced multi-mode AI coding agent for VS Code with specialized Architect, Code, and Debug personas. | Claude 3.7 Sonnet / DeepSeek-V3 | 75.8 | 67.2% | 64.2% | $0.40 | Open Source100% Free & Open Source (Apache 2.0). Connect directly to any model provider API. | Details |
| #8 | Aiderby Paul Gauthier • Autonomous CLI AgentThe premier open-source AI pair programmer in your terminal with git-native automated commits. | Claude 3.7 Sonnet + DeepSeek-R1 | 77.0 | 67.5% | 65.0% | $0.48 | Open Source100% Free & Open Source (Apache 2.0). Connects to Anthropic, OpenAI, DeepSeek, or local LLMs. | Details |
| #9 | Lovableby Lovable Labs • Full-Stack Web BuilderThe fastest full-stack AI software engineer for building and deploying production web apps from natural language. | Claude 3.7 Sonnet + GPT-4o | 73.5 | 63.5% | — | $0.60 | FreemiumFree tier with daily prompt credits | Details |
| #10 | v0 by Vercelby Vercel • Full-Stack Web BuilderVercel's generative UI and full-stack Next.js developer assistant for production React applications. | Claude 3.5 Sonnet / GPT-4o | 72.8 | 62.8% | — | $0.50 | FreemiumFree tier with 200 credits/month | Details |
| #11 | Bolt.newby StackBlitz • Full-Stack Web BuilderIn-browser full-stack AI development environment running Node.js and dev servers in WebContainers. | Claude 3.7 Sonnet / DeepSeek-V3 | 73.8 | 64.0% | — | $0.52 | FreemiumFree tier with daily tokens | Details |
| #12 | Replit Agentby Replit • Full-Stack Web BuilderAutonomous cloud application builder that creates, debugs, and hosts full-stack software from scratch. | Claude 3.5 Sonnet / Replit Ensemble | 72.5 | 63.0% | — | $0.65 | PaidIncluded with Replit Core ($25/mo or $20/mo billed annually) with checkpoints and cloud hosting. | Details |
| #13 | Augment Codeby Augment • In-IDE ExtensionEnterprise AI coding platform built for massive million-line codebases and complex multi-repo architectures. | Augment Code Intelligence Ensemble | 74.5 | 66.0% | 61.5% | $0.58 | PaidDeveloper Pro at $20/month | Details |
| #14 | Continueby Continue.dev • In-IDE ExtensionThe leading open-source AI code assistant for VS Code and JetBrains with full local model support. | Custom / Any (Claude 3.7, DeepSeek, Ollama) | 73.2 | 63.8% | 60.5% | $0.38 | Open Source100% Free & Open Source (Apache 2.0). Connect to any API or local LLM via Ollama. | Details |
| #15 | Traeby ByteDance • AI-First IDEAdaptive AI IDE by ByteDance featuring Builder Mode for project-wide autonomous engineering. | Claude 3.5 Sonnet / GPT-4o | 73.8 | 64.5% | 61.8% | $0.00 | 100% FreeCurrently completely Free during public release with complimentary Claude 3.5 Sonnet & GPT-4o usage. | Details |
| #16 | Supermavenby Anysphere (Cursor) • In-IDE ExtensionThe fastest code autocomplete engine with an unprecedented 1,000,000 token context window. | Babble (Proprietary 1M Context Model) | 72.0 | 61.0% | — | $0.20 | FreemiumFree tier with unlimited standard completions | Details |
| #17 | Gooseby Block (Square) • Autonomous CLI AgentBlock's open-source on-machine developer agent that automates complex engineering tasks via MCP. | Claude 3.7 Sonnet / Databricks DBRX | 73.5 | 65.2% | 63.0% | $0.45 | Open Source100% Free & Open Source (Apache 2.0). Connects to Anthropic, Databricks, OpenAI, or Ollama. | Details |
| #18 | Codyby Sourcegraph • In-IDE ExtensionSourcegraph's AI assistant powered by code graph indexing for multi-repo enterprise context. | Claude 3.5 Sonnet / GPT-4o | 72.8 | 63.5% | 60.0% | $0.50 | FreemiumFree tier with 200 completions/month | Details |