Commonsense Reasoning on StoryCloze
97.6AccuracyTraditional MTL
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Traditional MTL2024.05 | 97.6 | — | |
| Task ArithmeticValidation=true2024.05 | 95.3 | — | |
| Individual2024.05 | 94.9 | — | |
| Fisher MergingValidation=true2024.05 | 94.1 | — | |
| EMR-MERGINGValidation=false2024.05 | 93.6 | — | |
| RegMeanValidation=true2024.05 | 92.5 | — | |
| Weight AveragingValidation=false2024.05 | 92.5 | — | |
| Ties-MergingValidation=false2024.05 | 91.1 | — | |
| Ties-MergingValidation=true2024.05 | 90.3 | — | |
| PaLM 2-Lprompting=1-shot2023.05 | 87.4 | — | |
| PaLM 2-Mprompting=1-shot2023.05 | 86.7 | — | |
| PaLMprompting=1-shot2023.05 | 86.1 | — | |
| PaLM 2-Sprompting=1-shot2023.05 | 85.6 | — | |
| SALAD-7BInput Modality=Text, Parameters=7B2025.10 | 84.9 | -2 | |
| GPT-3Evaluation Protocol=1-shot2023.03 | 84.7 | — | |
| SALAD-3BInput Modality=Text, Parameters=3B2025.10 | 82.7 | 0.2 | |
| OPT-66BEvaluation Protocol=1-shot2023.03 | 81.83 | — | |
| GLM-4-Voice-9BInput Modality=Text, Parameters=9B2025.10 | 81.6 | 17.2 | |
| Task ArithmeticValidation=false2024.05 | 81.5 | — | |
| Qwen2-Audio-7BInput Modality=Text, Parameters=7B2025.10 | 81.1 | -0.2 | |
| DiVA-Llama3.1-8BInput Modality=Text, Parameters=8B2025.10 | 80.9 | 7.4 | |
| BloombergGPTEvaluation Protocol=1-shot2023.03 | 80.87 | — | |
| Qwen2.5-Omni-7BInput Modality=Text, Parameters=7B2025.10 | 80.5 | 4.5 | |
| BLOOM-176BEvaluation Protocol=1-shot2023.03 | 80.28 | — | |
| GPT-NeoXEvaluation Protocol=1-shot2023.03 | 78.3 | — | |
| DSIRModel Backbone=GPT-2 XL2026.02 | 67.72 | — | |
| PPLModel Backbone=GPT-2 XL2026.02 | 67.34 | — | |
| UltraFinewebModel Backbone=GPT-2 XL2026.02 | 67.13 | — | |
| OPUSModel Backbone=GPT-2 XL2026.02 | 67.13 | — | |
| DCLM-FastTextModel Backbone=GPT-2 XL2026.02 | 66.86 | — | |
| FineWeb-EduModel Backbone=GPT-2 XL2026.02 | 66.76 | — | |
| QuRatingModel Backbone=GPT-2 XL2026.02 | 66.7 | — | |
| RandomModel Backbone=GPT-2 XL2026.02 | 66.38 | — | |
| GREATSModel Backbone=GPT-2 XL2026.02 | 65.79 | — |