Coding Agent Leaderboard

Compare coding agents across models and harnesses

5 Results · 1 Models · 3 Harnesses · 2 Benchmarks

A Coding Agent is more than just a model - it's the combination of a Model and a Harness (the tool/framework driving the model). This leaderboard tracks how these components work together, because the same model can perform very differently depending on the harness it's paired with.
{
  • "headers": [
    • " ",
    • "Harness",
    • "Model ID",
    • "Precision",
    • "Model License",
    • "Harness License",
    • "Model Num Params (B)",
    • "Avg Score",
    • "swe-bench-verified",
    • "swe-bench-pro--ansible"
    ],
  • "data": [
    • [
      • "🟠",
      • "[Pi](https://github.com/earendil-works/pi/tree/main)",
      • "[RedHatAI/Qwen3.6-35B-A3B-NVFP4](https://huggingface.co/RedHatAI/Qwen3.6-35B-A3B-NVFP4)",
      • "nvfp4",
      • "FOSS",
      • "FOSS",
      • 35,
      • 0.5645,
      • 0.65,
      • 0.479
      ],
    • [
      • "🟠",
      • "[OpenCode](https://github.com/anomalyco/opencode)",
      • "[RedHatAI/Qwen3.6-35B-A3B-NVFP4](https://huggingface.co/RedHatAI/Qwen3.6-35B-A3B-NVFP4)",
      • "nvfp4",
      • "FOSS",
      • "FOSS",
      • 35,
      • 0.548,
      • 0.548,
      • ""
      ],
    • [
      • "🔶",
      • "[Claude Code](https://github.com/anthropics/claude-code)",
      • "[RedHatAI/Qwen3.6-35B-A3B-NVFP4](https://huggingface.co/RedHatAI/Qwen3.6-35B-A3B-NVFP4)",
      • "nvfp4",
      • "FOSS",
      • "Proprietary",
      • 35,
      • 0.545,
      • 0.632,
      • 0.458
      ]
    ],
  • "metadata": null
}