- AACR-Bench
- Agent Security Bench (ASB)
- AgentDojo
- AgentJudgeBench
- AGENTPI
- AIDev
- Berkeley Function Calling Leaderboard (BFCL)
- c-CRAB
- CAVE-Bench
- CodAGE
- CodeActInstruct
- CodeContests
- Defects4J
- EvoClaw
- FeatureBench
- IFEval-FC
- LiveCodeBench
- LoopsBench
- MCP-Bench
- MCPToolBench++
- MCPTox
- Multi-SWE-bench
- Multi-SWE-RL
- NL2Repo-Bench
- ProjectDev
- RepoComplianceBench
- Safe-OS
- SkillsBench
- SpecGenBench
- SWE-Bench
- SWE-bench-java-verified
- SWE-bench Lite-S
- SWE-bench Multimodal
- SWE-Bench+
- SWE-Bench Pro
- SWE-Bench Verified
- SWE-chat
- SWE-Compass
- SWE-Review-Bench
- SWE-Review-Traj
- τ-bench
- Terminal-Bench
- TM-Bench
- ToolACE
- TraceLab
- When2Tool