Skip to content

Commit f50bb47

Browse files
authored
docs: move evaluation position (zilliztech#193)
Signed-off-by: ChengZi <chen.zhang@zilliz.com>
1 parent 54cc336 commit f50bb47

File tree

1 file changed

+10
-10
lines changed

1 file changed

+10
-10
lines changed

README.md

Lines changed: 10 additions & 10 deletions
Original file line numberDiff line numberDiff line change
@@ -487,6 +487,16 @@ Get the current indexing status of a codebase. Shows progress percentage for act
487487

488488
---
489489

490+
## 📊 Evaluation
491+
492+
Our controlled evaluation demonstrates that Claude Context MCP achieves ~40% token reduction under the condition of equivalent retrieval quality. This translates to significant cost and time savings in production environments. This also means that, under the constraint of limited token context length, using Claude Context yields better retrieval and answer results.
493+
494+
![MCP Efficiency Analysis](assets/mcp_efficiency_analysis_chart.png)
495+
496+
For detailed evaluation methodology and results, see the [evaluation directory](evaluation/).
497+
498+
---
499+
490500
## 🏗️ Architecture
491501

492502
![](assets/Architecture.png)
@@ -666,16 +676,6 @@ Check the `/examples` directory for complete usage examples:
666676

667677
---
668678

669-
## 📊 Evaluation
670-
671-
Our controlled evaluation demonstrates that Claude Context MCP achieves ~40% token reduction under the condition of equivalent retrieval quality. This translates to significant cost and time savings in production environments. This also means that, under the constraint of limited token context length, using Claude Context yields better retrieval and answer results.
672-
673-
![MCP Efficiency Analysis](assets/mcp_efficiency_analysis_chart.png)
674-
675-
For detailed evaluation methodology and results, see the [evaluation directory](evaluation/).
676-
677-
---
678-
679679
## ❓ FAQ
680680

681681
**Common Questions:**

0 commit comments

Comments
 (0)