๐ป
LEADERBOARD
Code Generation
AI-powered code completion, generation, and transformation
22tools ranked
Code Generation Rankings
Ranked by overall ToolRoute Score across all benchmark dimensions
| Rank | Tool Name | ToolRoute Score | Output | Reliability | Efficiency | Cost | Trust | Stars |
|---|---|---|---|---|---|---|---|---|
| ๐ฅ | WindsurfOfficial | 83.0 | 86.0 | 80.0 | 84.0 | 50.0 | 82.0 | 6,000 |
| ๐ฅ | DevinOfficial | 82.0 | 86.0 | 76.0 | 72.0 | 30.0 | 80.0 | 5,000 |
| ๐ฅ | Sourcegraph CodyOfficial | 81.0 | 80.0 | 82.0 | 82.0 | 55.0 | 84.0 | 4,000 |
| #4 | Bolt.newOfficial | 79.0 | 82.0 | 76.0 | 84.0 | 70.0 | 78.0 | 8,000 |
| #5 | Replit AgentOfficial | 78.0 | 80.0 | 76.0 | 82.0 | 65.0 | 80.0 | 4,000 |
| #6 | Continue | 49.8 | 82.0 | 78.0 | 86.0 | 95.0 | 10.0 | 31,888 |
| #7 | Aider | 49.7 | 88.0 | 80.0 | 82.0 | 80.0 | 10.0 | 42,016 |
| #8 | CodeiumOfficial | 49.4 | 84.0 | 80.0 | 88.0 | 90.0 | 10.0 | 5,111 |
| #9 | GitHub CopilotOfficial | 47.9 | 90.0 | 86.0 | 88.0 | 50.0 | 10.0 | 11,441 |
| #10 | CodestralOfficial | 47.8 | 86.0 | 82.0 | 84.0 | 65.0 | 10.0 | 868 |
| #11 | StarCoder2 | 47.7 | 82.0 | 78.0 | 86.0 | 95.0 | 10.0 | 2,047 |
| #12 | CursorOfficial | 47.3 | 90.0 | 84.0 | 86.0 | 45.0 | 10.0 | 32,452 |
| #13 | QodoOfficial | 47.0 | 80.0 | 80.0 | 82.0 | 70.0 | 10.0 | 10,552 |
| #14 | OpenAI CodexOfficial | 46.3 | 82.0 | 82.0 | 80.0 | 55.0 | 10.0 | 30,270 |
| #15 | TabnineOfficial | 45.9 | 78.0 | 80.0 | 86.0 | 65.0 | 10.0 | 1,430 |
| #16 | Context7Official | 9.3 | 9.5 | 9.0 | 8.5 | 8.0 | 8.7 | 49,303 |
| #17 | GitHub MCP ServerOfficial | 9.3 | 9.2 | 8.8 | 8.5 | 8.0 | 9.3 | 27,952 |
| #18 | GitLab MCPOfficial | 9.2 | 8.8 | 8.8 | 8.5 | 8.5 | 9.0 | 81,246 |
| #19 | Figma Context MCP | 9.0 | 9.0 | 8.5 | 8.5 | 8.0 | 8.4 | 13,725 |
| #20 | SonarQube MCP Server | 7.8 | 8.2 | 8.2 | 7.5 | 8.0 | 8.0 | 720 |
| #21 | TailwindCSS MCP | 7.5 | 7.0 | 7.0 | 8.0 | 9.0 | 6.5 | 750 |
| #22 | Storybook MCP | 7.1 | 7.0 | 6.8 | 7.5 | 8.0 | 6.5 | 600 |
Score Guide
9.0+ Exceptional
8.0+ Excellent
7.0+ Good
6.0+ Fair
<6.0 Below Average
Contribute Benchmark Data
Help improve these rankings by submitting real-world telemetry. Contributors earn routing credits for every data point.