Skip to content

Turbocharge Claude Code, Cursor, Codex, Gemini & every coding agent: faster, cheaper, with contextual understanding specific to your codebase.

docs: reword hero headline to match the efficiency table's own numbers

Claude630cd1deb765
diff --git a/README.md b/README.md
index fde61634..1e551bdc 100644
--- a/README.md
+++ b/README.md
@@ -16,7 +16,7 @@
<a href="https://scorecard.dev/viewer/?uri=github.com/NanoNets/Graft"><img src="https://img.shields.io/ossf-scorecard/github.com/NanoNets/Graft?style=for-the-badge&label=openssf%20scorecard" /></a>
</p>
-### Up to **4× cheaper** and **3× faster**, with better or no loss of correctness.
+### Up to **2× cheaper** and **2.5× faster**, with better or no loss of correctness.
| Metric | Cold Claude Code | Claude Code with graft |
|---|---|---|
@@ -25,7 +25,7 @@
| Time savings | Baseline | **+60%** |
| Correctness | 54% | **66% (+12 pts)** |
-<sub>Efficiency is a 162-run controlled benchmark (same agent, same file tools, only the context differs). Correctness is **SWE-bench Verified**, graded by the official harness — graft resolved 66% of instances tested against Cold Claude Code's 54%. The "up to 4× cheaper / 3× faster" figures are the biggest single-task wins from a separate real-repo sweep (PocketBase, ollama, Excalidraw). [Efficiency method ↓](#benchmark) · [SWE-bench ↓](#swe-bench-verified) · [Per-repo numbers ↓](#tested-on-your-popular-repos)</sub>
+<sub>Efficiency is a 162-run controlled benchmark (same agent, same file tools, only the context differs). Correctness is **SWE-bench Verified**, graded by the official harness — graft resolved 66% of instances tested against Cold Claude Code's 54%. [Efficiency method ↓](#benchmark) · [SWE-bench ↓](#swe-bench-verified) · [Per-repo numbers ↓](#tested-on-your-popular-repos)</sub>
</div>