Spaces:
Sleeping
Sleeping
File size: 1,428 Bytes
0646b18 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 | # Full Matrix Comparison: Multiple Providers x Multiple Modes
# Compare all combinations of providers and modes
profiling:
configs:
- "settings.openai.toml"
- "settings.azure.toml"
- "settings.groq.toml"
modes:
- "balanced"
tasks:
- "test_get_top_account_by_revenue_stream"
runs: 3
langfuse:
host: "https://cloud.langfuse.com"
retry:
max_attempts: 10
initial_delay: 7.0
experiment:
name: "full_matrix_comparison"
description: "Compare OpenAI vs Azure vs Groq across Fast and Balanced modes (3x2 matrix)"
runs:
- name: "openai_balanced"
test_id: "settings.openai.toml:balanced:test_get_top_account_by_revenue_stream"
iterations: 3
output: "experiments/openai_balanced_{{timestamp}}.json"
env:
MODEL_NAME: "Azure/gpt-4o"
- name: "azure_balanced"
test_id: "settings.azure.toml:balanced:test_get_top_account_by_revenue_stream"
iterations: 3
output: "experiments/azure_balanced_{{timestamp}}.json"
env:
MODEL_NAME: null
- name: "groq_balanced"
test_id: "settings.groq.toml:balanced:test_get_top_account_by_revenue_stream"
iterations: 3
output: "experiments/groq_balanced_{{timestamp}}.json"
env:
MODEL_NAME: openai/gpt-oss-20b
comparison:
generate_html: true
html_output: "experiments/comparison.html"
auto_open: true
|