Our new X account is live! Follow @wizwand_team for updates

Common Sense Reasoning on HSWAG

0.9751Accuracy

In-Squeeze

Updated 3d ago

Evaluation Results

Method	Links
In-Squeeze 2026.02		0.9751
In-Squeeze 2026.02		0.9749
Cont-Squeeze 2026.02		0.9742
Direct Fine-tuning 2026.02		0.9719
Direct Fine-tuning 2026.02		0.9719
Cont-Squeeze 2026.02		0.9716
Direct Fine-tuning 2026.02		0.9709
Cont-Squeeze 2026.02		0.9679
In-Squeeze 2026.02		0.9058
In-Squeeze 2026.02		0.8976
Direct Fine-tuning 2026.02		0.8914
Cont-Squeeze 2026.02		0.8889
Cont-Squeeze 2026.02		0.8841
Direct Fine-tuning 2026.02		0.8799
Direct Fine-tuning 2026.02		0.8711
Qwen3-4B 2025.12		0.7946
Llama-3.1 2026.01		0.76
Qwen2.5-3B 2025.12		0.7385
llama-3.2-3B 2025.12		0.7106
SmolLM3-3B 2025.12		0.692
GenKnowSub 2025.05		0.6796
Phi-2 2025.05		0.6675
GenKnowSub 2025.05		0.6675
Arrow 2025.05		0.6641
gemma2-2B 2025.12		0.662
Cont-Squeeze 2026.02		0.6555
SmolLM2-1.7B 2025.12		0.653
Qwen2.5-1.5B 2025.12		0.6418
OLMo-2-0425-1B 2025.12		0.6161
YuLan-Mini-2.4B 2025.12		0.612
Qwen2-1.5B 2025.12		0.6077
Qwen3-1.7B 2025.12		0.6076
llama-3.2-1B 2025.12		0.602
DiffuLlama 2026.01		0.587
A3 2026.01		0.584
PCMind-2.1-Kaiyuan-2B 2025.12		0.5813
Zero-shot 2026.02		0.508
A3 2026.01		0.496
Qwen3-0.6B 2025.12		0.4851
EMR-MERGING 2024.05		0.447
Individual 2024.05		0.444
Ties-Merging 2024.05		0.428
Ties-Merging 2024.05		0.426
Traditional MTL 2024.05		0.423
Fisher Merging 2024.05		0.422
Task Arithmetic 2024.05		0.415
A3 2026.01		0.402
RegMean 2024.05		0.401
Weight Averaging 2024.05		0.401
Plaid 2026.01		0.393
Task Arithmetic 2024.05		0.314
Dream 2026.01		0.269