GAIA Validation - GPT-5
Cross-Model Comparison
See how GPT-5 compares to other models on GAIA and other benchmarks in the Model Comparison Leaderboard.
MiroFlow supports GPT-5 with MCP tool invocation, providing a unified workflow for multi-step reasoning, information integration, and scalable tool coordination.
Prerequisites
Before proceeding, please review the GAIA Validation Prerequisites document, which covers common setup requirements, dataset preparation, and API key configuration.
Running the Evaluation
Step 1: Dataset Preparation
Follow the dataset preparation instructions in the prerequisites document.
Step 2: API Keys Configuration
Configure the following API keys in your .env file:
# Search and web scraping capabilities
SERPER_API_KEY="your-serper-api-key"
JINA_API_KEY="your-jina-api-key"
# Code execution environment
E2B_API_KEY="your-e2b-api-key"
# Vision understanding capabilities
ANTHROPIC_API_KEY="your-anthropic-api-key"
GEMINI_API_KEY="your-gemini-api-key"
# Primary LLM provider, LLM judge, reasoning, and hint generation
OPENAI_API_KEY="your-openai-api-key"
OPENAI_BASE_URL="https://api.openai.com/v1"
Step 3: Run the Evaluation
Configuration Note
To run with GPT-5, create a custom config based on the standard configs with a GPT-5 LLM provider (GPT5OpenAIClient). See YAML Configuration Guide for details on creating custom configurations.
Step 4: Monitor Progress
Follow the progress monitoring instructions in the prerequisites document.
Documentation Info
Last Updated: February 2026 · Doc Contributor: Team @ MiroMind AI