List your company
ResearchFormerly WizWand

Multistep Reasoning on MuSR

73.33AccuracySpurious Universal
39.186848.050956.91565.7791Oct 21, 2025Nov 26, 2025Jan 2, 2026Feb 7, 2026Mar 16, 2026Apr 21, 2026May 28, 2026
Updated 5mo ago

Evaluation results

MethodLinks
Spurious UniversalModel=Qwen/Qwen3.5-27B2026.0573.33
PromptWizardModel=Qwen/Qwen3.5-27B2026.0571.33
Step-BackModel=Qwen/Qwen3.5-27B2026.0570
Plan-and-SolveModel=Qwen/Qwen3.5-27B2026.0570
SpuriousModel=Qwen/Qwen3.5-27B2026.0569.33
PromptWizardModel=allenai/Olmo-3-7B-Instruct2026.0567.33
SpuriousModel=allenai/Olmo-3-7B-Instruct2026.0566
Re-ReadingModel=meta-llama/Llama-3.2-1B-Instruct2026.0564
Re-ReadingModel=Qwen/Qwen3.5-27B2026.0564
Plan-and-SolveModel=meta-llama/Llama-3.2-1B-Instruct2026.0562
Spurious UniversalModel=allenai/Olmo-3-7B-Instruct2026.0562
Least-to-MostModel=Qwen/Qwen3.5-27B2026.0562
SpuriousModel=meta-llama/Llama-3.2-1B-Instruct2026.0560.67
Zero-Shot CoTModel=Qwen/Qwen3.5-0.8B2026.0560
SpuriousModel=Qwen/Qwen3.5-0.8B2026.0559.2
Plan-and-SolveModel=Qwen/Qwen3.5-0.8B2026.0558
AnalogicalModel=Qwen/Qwen3.5-27B2026.0558
Zero-Shot CoTModel=Qwen/Qwen3.5-27B2026.0558
Step-BackModel=meta-llama/Llama-3.2-1B-Instruct2026.0556
AnalogicalModel=meta-llama/Llama-3.2-1B-Instruct2026.0556
Self-AskModel=meta-llama/Llama-3.2-1B-Instruct2026.0556
Self-AskModel=allenai/Olmo-3-7B-Instruct2026.0556
Step-BackModel=Qwen/Qwen3.5-0.8B2026.0554
Spurious UniversalModel=Qwen/Qwen3.5-0.8B2026.0554
PromptWizardModel=meta-llama/Llama-3.2-1B-Instruct2026.0554
Spurious UniversalModel=meta-llama/Llama-3.2-1B-Instruct2026.0554
Step-BackModel=allenai/Olmo-3-7B-Instruct2026.0554
Re-ReadingModel=allenai/Olmo-3-7B-Instruct2026.0554
Self-AskModel=Qwen/Qwen3.5-27B2026.0554
RTNModel=Qwen3.5-27B, Group Size (g)=162026.0553.7
PromptWizardModel=Qwen/Qwen3.5-0.8B2026.0553.33
BF16Model=Qwen3.5-27B2026.0552.5
AWQModel=Qwen3.5-27B, Group Size (g)=162026.0552
Self-AskModel=Qwen/Qwen3.5-0.8B2026.0552
Zero-Shot CoTModel=meta-llama/Llama-3.2-1B-Instruct2026.0552
AAACModel=Qwen3.5-27B, Group Size (g)=162026.0551.6
IF4Model=Qwen3.5-27B, Group Size (g)=162026.0551.3
AnalogicalModel=Qwen/Qwen3.5-0.8B2026.0550
AnalogicalModel=allenai/Olmo-3-7B-Instruct2026.0550
Re-ReadingModel=Qwen/Qwen3.5-0.8B2026.0548
Least-to-MostModel=Qwen/Qwen3.5-0.8B2026.0546
Plan-and-SolveModel=allenai/Olmo-3-7B-Instruct2026.0546
Zero-Shot CoTModel=allenai/Olmo-3-7B-Instruct2026.0546
AWQModel=Qwen3.5-9B, Group Size (g)=162026.0544.2
AAACModel=Qwen3.5-9B, Group Size (g)=162026.0544.2
BF16Model=Qwen3.5-9B2026.0543.4
RTNModel=Qwen3.5-9B, Group Size (g)=162026.0542.1
Least-to-MostModel=meta-llama/Llama-3.2-1B-Instruct2026.0542
Least-to-MostModel=allenai/Olmo-3-7B-Instruct2026.0542
SePTBackbone=Qwen2.5-Math-7B2025.1041.5
BaseBackbone=Qwen2.5-Math-7B2025.1041.4
GRPOBackbone=Qwen2.5-Math-7B2025.1041.4
IF4Model=Qwen3.5-9B, Group Size (g)=162026.0540.5