List your company

Mathematical Reasoning on GSM8K (Accuracy, #Tokens)

97.17AccuracyMC²
84.918888.099491.2894.4606Apr 19, 2026

Evaluation results

MethodLinks
MC²Backbone=Gemini-2.0-flash, Reasoning Method=MC²2026.0497.17573
MC²Backbone=GPT-4o-mini, Reasoning Method=MC²2026.0496.92833
MC²Backbone=Qwen3-8B, Reasoning Method=MC²2026.0496.66726
CoT-SCBackbone=Gemini-2.0-flash, Reasoning Method=CoT-SC2026.0496.031,100
ToTBackbone=Gemini-2.0-flash, Reasoning Method=ToT2026.0495.98558
Buffer of ThoughtBackbone=Gemini-2.0-flash, Reasoning Method=Buffer of Thought2026.0495.961,324
Meta ReasoningBackbone=Gemini-2.0-flash, Reasoning Method=Meta Reasoning2026.0495.83219
CoTBackbone=Gemini-2.0-flash, Reasoning Method=CoT2026.0495.58218
MC²Backbone=Llama-3.1-8B-Instruct, Reasoning Method=MC²2026.0495.551,320
Meta PromptBackbone=Gemini-2.0-flash, Reasoning Method=Meta Prompt2026.0495.431,111
Meta PromptBackbone=Qwen3-8B, Reasoning Method=Meta Prompt2026.0494.62522
CoT-SCBackbone=GPT-4o-mini, Reasoning Method=CoT-SC2026.0494.441,805
ToTBackbone=GPT-4o-mini, Reasoning Method=ToT2026.0494.411,016
CoT-SCBackbone=Qwen3-8B, Reasoning Method=CoT-SC2026.0494.411,537
ToTBackbone=Qwen3-8B, Reasoning Method=ToT2026.0494.09877
Meta ReasoningBackbone=Qwen3-8B, Reasoning Method=Meta Reasoning2026.0494.06306
Meta ReasoningBackbone=GPT-4o-mini, Reasoning Method=Meta Reasoning2026.0493.96361
Buffer of ThoughtBackbone=GPT-4o-mini, Reasoning Method=Buffer of Thought2026.0493.781,373
Buffer of ThoughtBackbone=Qwen3-8B, Reasoning Method=Buffer of Thought2026.0493.681,316
CoTBackbone=Qwen3-8B, Reasoning Method=CoT2026.0493.45305
Meta PromptBackbone=GPT-4o-mini, Reasoning Method=Meta Prompt2026.0493.41,042
TTPIBackbone=GPT-4o-mini, Reasoning Method=TTPI2026.0492.5874
CoTBackbone=GPT-4o-mini, Reasoning Method=CoT2026.0491.38358
Meta PromptBackbone=Llama-3.1-8B-Instruct, Reasoning Method=Meta Prompt2026.0490.441,217
TTPIBackbone=Llama-3.1-8B-Instruct, Reasoning Method=TTPI2026.0490.171,426
TTPIBackbone=Qwen3-8B, Reasoning Method=TTPI2026.0489.74300
ToTBackbone=Llama-3.1-8B-Instruct, Reasoning Method=ToT2026.0487.671,478
CoT-SCBackbone=Llama-3.1-8B-Instruct, Reasoning Method=CoT-SC2026.0487.291,936
Buffer of ThoughtBackbone=Llama-3.1-8B-Instruct, Reasoning Method=Buffer of Thought2026.0486.681,745
Meta ReasoningBackbone=Llama-3.1-8B-Instruct, Reasoning Method=Meta Reasoning2026.0486.55447
CoTBackbone=Llama-3.1-8B-Instruct, Reasoning Method=CoT2026.0485.39528