Update docs with benchmark results #5
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
- Added COT_SYSTEM_PROMPT constant for reasoning instruction - Modified model validators in both MessagesRequest and TokenCountRequest to add CoT prompt for Sonnet models - Updated CAPABILITIES.md to document the automatic CoT functionality - COT system prompt is added automatically for all Sonnet models while keeping Haiku models without it - Verified implementation with dedicated cot_reasoning test 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>
- Added performance timing comparison between Claude and Deepseek models - Removed unnecessary image from README - Added note about using 127.0.0.1 instead of localhost for connection issues - Improved formatting and clarity 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>
- Add clear explanation of proxy functionality - Restructure content into logical sections - Add detailed information about Chain-of-Thought prompting - Improve formatting and organization - Add technical details and limitations sections - Update model mapping information 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>
- Map Claude Haiku requests to Gemini Flash 2.0 - Keep Claude Sonnet requests mapped to Deepseek-chat - Add support for Gemini API key in environment variables - Update documentation to reflect new dual-provider approach - Update tests to use appropriate models for different tasks 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>
…ults - Add new comparison_tests.py script for benchmark testing - Update README with accurate performance metrics - Update CAPABILITIES with latest benchmark findings - Fix Pydantic compatibility issues in server.py
- Added PERFORMANCE_SUMMARY.md with detailed performance metrics - Updated README.md with accurate performance comparison data - Created benchmark tools and scripts for direct API comparison - Added performance formula for estimating task completion times - Added test scripts for both proxy and direct API testing 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.