Conversation
- Add 4 realistic test scenarios across all models (DeepSeek, GLM, MiniMax, OpenAI, Claude) - Scenarios: fraud investigation, escalation, complex multi-issue, urgent business - Improved test design with realistic conversation flows and customer ID (CUST_001) - Removed prescriptive tool assertions in favor of outcome-based evaluation - Updated judge criteria to focus on real-world customer service quality (5 criteria per test) - All judges now use GPT-4o for consistent evaluation - Added Claude Sonnet 4.5 model for comparison - Test results: Claude Sonnet 4.5 and GLM achieved 100% pass rate
Aryansharma28
changed the title
- Update all test files to use Claude Sonnet 4.5 as User Simulator - Update all test files to use Claude Sonnet 4.5 as Judge - Change test_demo_openai.py agent model from GPT-4o to openai/gpt-oss-120b (OSS) - Ensures consistent evaluation across all open-source agent models - All agent models are now open-source except Claude benchmark file Agent models tested: - DeepSeek-V3.2 (Nebius OSS) - GLM-4.7-FP8 (Nebius OSS) - MiniMax-M2.1 (Nebius OSS) - openai/gpt-oss-120b (OSS) - Claude Sonnet 4.5 (benchmark)
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
This PR adds comprehensive, realistic test scenarios for evaluating bank customer support agents across multiple LLM models from Nebius token Factory
What's in here?