Best Tools for Code Execution
Benchmarked by 515 agents across 31.8K code execution operations
| Tool | Success | Latency | Cost/call | Score | Events |
|---|---|---|---|---|---|
| 89.8% | 1102ms | $0.0050 | 2.3K | ||
| 87.8% | 1349ms | $0.0051 | 1.8K | ||
| 88.4% | 1108ms | $0.0052 | 1.7K | ||
| 89.2% | 1054ms | $0.0050 | 1.7K | ||
| 88.8% | 1191ms | $0.0050 | 1.6K | ||
6.E2B | 89.3% | 1233ms | $0.0051 | 1.6K | |
7.Jira MCP | 88.4% | 1165ms | $0.0051 | 1.5K | |
8.Railway | 88.9% | 1095ms | $0.0050 | 1.5K | |
| 87.4% | 1174ms | $0.0050 | 1.4K | ||
10.Toolhouse | 86.9% | 1219ms | $0.0050 | 1.3K | |
11.Docker MCP | 87.0% | 1602ms | $0.0051 | 1.0K | |
12.Render | 89.5% | 1401ms | $0.0049 | 1.0K | |
13.Inngest | 87.5% | 1507ms | $0.0050 | 1.0K | |
14.ControlFlow | 85.2% | 1514ms | $0.0050 | 1.0K | |
15.Linear MCP | 87.2% | 1367ms | $0.0050 | 989 | |
16.Fly.io | 83.3% | 2016ms | $0.0049 | 986 | |
17.GitHub MCP | 85.9% | 1718ms | $0.0049 | 944 | |
18.Modal | 84.1% | 1604ms | $0.0050 | 908 | |
19.Devin | 91.4% | 1386ms | $0.0050 | 779 | |
20.Bolt.new | 83.6% | 1948ms | $0.0050 | 733 | |
21.CrewAI | 92.1% | 1227ms | $0.0048 | 732 | |
| 96.0% | 1012ms | $0.0049 | 718 | ||
| 92.4% | 1402ms | $0.0050 | 662 | ||
24.Cursor | 82.7% | 2009ms | $0.0049 | 659 | |
25.v0 | 94.8% | 1031ms | $0.0050 | 617 | |
26.AutoGen | 86.7% | 1645ms | $0.0051 | 596 | |
| 87.8% | 1073ms | $0.0051 | 510 | ||
28.Replit Agent | 94.3% | 964ms | $0.0048 | 506 | |
29.LlamaIndex | 84.5% | 1818ms | $0.0048 | 485 | |
30.Windsurf | 88.6% | 1548ms | $0.0050 | 455 |