Reasoning Tasks
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Zero-shot Reasoning | Reasoning Tasks (BoolQ, PIQA, HellaSwag, WinoGrande, ARC-e, ARC-c, OBQA) Zero-shot | BoolQ Accuracy (Zero-shot)82.813 | 64 | |
| Zero-shot Reasoning | Zero-Shot Reasoning Tasks (ARC-C, ARC-E, BoolQ, Hella, OBQA, PIQA, SIQA, Wino) | ARC-C Accuracy65.53 | 54 | |
| Reasoning | Reasoning Tasks Average | Average Score68.6 | 32 | |
| Zero-shot Reasoning | Zero-shot Reasoning Tasks (ARC-e, ARC-c, BoolQ, Hellaswag, WinoGrande, MMLU) | ARC-e Accuracy (Zero-shot)77.1 | 20 | |
| Single-turn Reasoning | Reasoning Tasks AIME24, AIME25, GPQA | AIME 2024 Accuracy92.2 | 18 | |
| Zero-shot Reasoning | Reasoning Tasks ARC-C, BoolQ, HellaSwag, MathQA, MMLU, Race | ARC-C Accuracy50.43 | 14 | |
| Zero-shot Evaluation | Reasoning Tasks Zero-shot (PI, AE, AC, HS, WG, LB) | PI Score (Zero-shot)81.6 | 13 | |
| Zero-shot Evaluation | Reasoning tasks | Reasoning Accuracy70.7 | 7 | |
| Model Ranking Prediction | Reasoning Tasks Aggregate | Spearman Rho0.81 | 6 | |
| Reasoning Chain Optimization | Reasoning Tasks | Query Count47 | 3 |
Showing 10 of 10 rows