List your company
ResearchFormerly WizWand

Logical Reasoning on Game-of-24

94.33AccuracyMC²
4.203627.60185174.3982Apr 19, 2026
Updated 6mo ago

Evaluation results

MethodLinks
MC²Backbone=Gemini-2.0-flash, Reasoning Method=MC²2026.0494.331,219
MC²Backbone=GPT-4o-mini, Reasoning Method=MC²2026.0488.672,479
Meta PromptBackbone=Gemini-2.0-flash, Reasoning Method=Meta Prompt2026.04881,592
ToTBackbone=Gemini-2.0-flash, Reasoning Method=ToT2026.0483.335,549
Meta ReasoningBackbone=Gemini-2.0-flash, Reasoning Method=Meta Reasoning2026.04811,682
CoT-SCBackbone=Gemini-2.0-flash, Reasoning Method=CoT-SC2026.0480.673,085
MC²Backbone=Qwen3-8B, Reasoning Method=MC²2026.0480.674,445
Buffer of ThoughtBackbone=Gemini-2.0-flash, Reasoning Method=Buffer of Thought2026.04782,158
CoTBackbone=Gemini-2.0-flash, Reasoning Method=CoT2026.0472599
CoT-SCBackbone=Qwen3-8B, Reasoning Method=CoT-SC2026.0468.677,325
ToTBackbone=Qwen3-8B, Reasoning Method=ToT2026.0461.676,562
TTPIBackbone=Qwen3-8B, Reasoning Method=TTPI2026.0458.676,410
CoTBackbone=Qwen3-8B, Reasoning Method=CoT2026.04482,960
Meta PromptBackbone=Qwen3-8B, Reasoning Method=Meta Prompt2026.04487,393
Meta ReasoningBackbone=Qwen3-8B, Reasoning Method=Meta Reasoning2026.0447.332,818
Buffer of ThoughtBackbone=Qwen3-8B, Reasoning Method=Buffer of Thought2026.0445.672,880
MC²Backbone=Llama-3.1-8B-Instruct, Reasoning Method=MC²2026.0445.3312,808
Meta PromptBackbone=GPT-4o-mini, Reasoning Method=Meta Prompt2026.0441.333,178
Meta PromptBackbone=Llama-3.1-8B-Instruct, Reasoning Method=Meta Prompt2026.044122,895
ToTBackbone=GPT-4o-mini, Reasoning Method=ToT2026.0433.333,801
ToTBackbone=Llama-3.1-8B-Instruct, Reasoning Method=ToT2026.043315,249
TTPIBackbone=Llama-3.1-8B-Instruct, Reasoning Method=TTPI2026.043315,106
Meta ReasoningBackbone=Llama-3.1-8B-Instruct, Reasoning Method=Meta Reasoning2026.0432.6712,631
Buffer of ThoughtBackbone=Llama-3.1-8B-Instruct, Reasoning Method=Buffer of Thought2026.0428.676,146
TTPIBackbone=GPT-4o-mini, Reasoning Method=TTPI2026.0428916
CoT-SCBackbone=GPT-4o-mini, Reasoning Method=CoT-SC2026.04272,461
CoT-SCBackbone=Llama-3.1-8B-Instruct, Reasoning Method=CoT-SC2026.042430,741
Meta ReasoningBackbone=GPT-4o-mini, Reasoning Method=Meta Reasoning2026.0420.33964
Buffer of ThoughtBackbone=GPT-4o-mini, Reasoning Method=Buffer of Thought2026.0419.331,539
CoTBackbone=Llama-3.1-8B-Instruct, Reasoning Method=CoT2026.0416.6714,734
CoTBackbone=GPT-4o-mini, Reasoning Method=CoT2026.047.67553