Failure Mode Explorer Report

Generated on: 2025-04-23 10:49:06

Threshold (minimum child nodes): 5

Percentile for stability classification: 20%

Selected Model:
gemma-3-4b-it
Mistral-7B-Instruct-v0.3
Meta-Llama-3.1-70B-Instruct
Phi-4-mini-instruct
QwQ-32B
claude3.7-sonnet-20250219
gemma-3-27b-it
deepseek-r1-250120
Qwen2.5-32B-Instruct
qwen-max-2024-10-15
gpt-4o-2024-11-20
hunyuan-standard-2025-02-10
doubao-1-5-pro-32k-250115
deepseek-v3-250324
Qwen2.5-72B-Instruct
Qwen2.5-7B-Instruct
Meta-Llama-3.1-8B-Instruct

Total analyzed nodes: 1122

Systematic (stable) threshold (lower 20%): 0.5000

Occasional (unstable) threshold (upper 20%): 1.4718

Systematic (Stable) Patterns

Occasional (Unstable) Patterns