Sentence Stress Reasoning on StressPresso
89.6SSR AccuracyHuman Annotators
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| Human AnnotatorsCategory=Human, Trans.=False, Stress=False, Audio=True2025.05 | 89.6 | 96 | — | |
| StresSLMCategory=SLM, Trans.=False, Stress=False, Audio=True2025.05 | 87.6 | — | — | |
| gpt-4oCategory=Text LLM, Trans.=True, Stress=True, Audio=False2025.05 | 83.6 | — | — | |
| Llama-3.1-8B-InstructCategory=Text LLM, Trans.=True, Stress=True, Audio=False2025.05 | 81.1 | — | — | |
| gpt-4o-miniCategory=Text LLM, Trans.=True, Stress=True, Audio=False2025.05 | 80.1 | — | — | |
| WhiStress → gpt-4oCategory=Cascade Pipeline, Trans.=False, Stress=False, Audio=True2025.05 | 79.7 | — | — | |
| WhiStress → Llama-3.1-8B-InstructCategory=Cascade Pipeline, Trans.=False, Stress=False, Audio=True2025.05 | 76.2 | — | — | |
| Qwen2-7B-InstructCategory=Text LLM, Trans.=True, Stress=True, Audio=False2025.05 | 74.2 | — | — | |
| WhiStress → gpt-4o-miniCategory=Cascade Pipeline, Trans.=False, Stress=False, Audio=True2025.05 | 73.2 | — | — | |
| Gemini-2.5-ProCategory=SLM, Trans.=False, Stress=False, Audio=True2025.05 | 72.7 | — | — | |
| WhiStress → Qwen2-7B-InstructCategory=Cascade Pipeline, Trans.=False, Stress=False, Audio=True2025.05 | 69.3 | — | — | |
| Qwen-7B-ChatCategory=Text LLM, Trans.=True, Stress=True, Audio=False2025.05 | 64.8 | — | — | |
| gpt-4o-audioCategory=SLM, Trans.=False, Stress=False, Audio=True2025.05 | 64.8 | — | — | |
| Qwen3-Omni-30B-InstructCategory=SLM, Trans.=False, Stress=False, Audio=True2025.05 | 64.8 | — | — | |
| WhiStress → Qwen-7B-ChatCategory=Cascade Pipeline, Trans.=False, Stress=False, Audio=True2025.05 | 62.3 | — | — | |
| Audio-Flamingo-3Category=SLM, Trans.=False, Stress=False, Audio=True2025.05 | 52.9 | — | — | |
| LLaMA-OmniCategory=SLM, Trans.=False, Stress=False, Audio=True2025.05 | 52.9 | — | — | |
| SALMONNCategory=SLM, Trans.=False, Stress=False, Audio=True2025.05 | 52.4 | — | — | |
| Qwen2Audio-7B-InstructCategory=SLM, Trans.=False, Stress=False, Audio=True2025.05 | 51.4 | — | — | |
| Phi-4-multimodal-instructCategory=SLM, Trans.=False, Stress=False, Audio=True2025.05 | 50.4 | — | — | |
| Audio-Flamingo-32025.05 | — | — | 2.39 | |
| Gemini-2.5-Pro2025.05 | — | — | 3.29 | |
| gpt-4o-audio2025.05 | — | — | 2.84 | |
| LLaMA-Omni2025.05 | — | — | 1.92 | |
| Phi-4-multimodal-instruct2025.05 | — | — | 2.73 | |
| Qwen2Audio-7B-Instruct2025.05 | — | — | 2.79 | |
| Qwen3-Omni-30B-Instruct2025.05 | — | — | 2.42 | |
| SALMONN2025.05 | — | — | 2.19 | |
| StresSLM2025.05 | — | — | 3.83 |