List your company

Open-ended stress reasoning on StressTest

3.82Open SSR ScoreGemini-2.5-Pro
1.81282.33392.8553.3761May 28, 2025

Evaluation results

MethodLinks
Gemini-2.5-Pro2025.053.82
StresSLM2025.053.7
gpt-4o-audio2025.053.09
Qwen2Audio-7B-Instruct2025.052.84
Audio-Flamingo-32025.052.62
Qwen3-Omni-30B-Instruct2025.052.51
Phi-4-multimodal-instruct2025.052.23
SALMONN2025.052.07
LLaMA-Omni2025.051.89