Add real benchmark data with ReAct agent#10
Merged
Conversation
- ReAct agent with 4 tools (calculator, search_knowledge, unit_converter, date_info) - Uses raw Anthropic API calls (no framework dependencies) - 7 test cases from easy to adversarial, 20 trials each - Results: 94.3% overall pass rate (89.1%-97.1% CI), ARS 79.7/100 - Key finding: simple-math at 70% due to comma formatting variance - Includes flamegraph HTML, baseline JSON, and terminal output Model: claude-3-haiku-20240307 | Total cost: $0.11 Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
claude-3-haiku-20240307simple-mathat 70% due to comma formatting variance ("4,446" vs "4446")Files
agent.py— ReAct agent implementation (Anthropic + Google support)agentrial.yml— Test suite with 7 casesresults_haiku.json— Full JSON results (166KB)flamegraph_haiku.html— Interactive trajectory flame graphbaseline.json— Baseline for regression detectionterminal_pretty.txt/ars_output.txt— Terminal outputs for screenshotsTest plan
🤖 Generated with Claude Code