List your company

Mathematical Reasoning on AIME24 (Inference Latency)

12.2Latency (s)T2
-28.128244.086516.3788.514Jan 29, 2026

Evaluation results

MethodLinks
T2Backbone=Llama3.1-8B2026.0112.2
T2Backbone=Qwen2.5-7B2026.0125.6
Std-PTBackbone=Llama3.1-8B2026.0128.3
ESCBackbone=Qwen2.5-7B2026.0130
Std-PTBackbone=Qwen2.5-7B2026.0131.2
DSCBackbone=Llama3.1-8B2026.0146.1
ESCBackbone=Llama3.1-8B2026.0146.4
T2Backbone=Qwen3-4B2026.0151.6
DSCBackbone=Qwen2.5-7B2026.0157.1
Std-PTBackbone=Qwen3-4B2026.0165.3
DeepConfBackbone=Qwen2.5-7B2026.0198.6
ACBackbone=Llama3.1-8B2026.01100.7
ACBackbone=Qwen2.5-7B2026.01108
DeepConfBackbone=Llama3.1-8B2026.01113.8
ESCBackbone=Qwen3-4B2026.01126
DSCBackbone=Qwen3-4B2026.01144.3
T2Backbone=Deepseek-R1-Distill-Qwen-7B2026.01145.5
ACBackbone=Qwen3-4B2026.01203.7
Std-PTBackbone=Deepseek-R1-Distill-Qwen-7B2026.01204.9
DeepConfBackbone=Qwen3-4B2026.01302.3
ESCBackbone=Deepseek-R1-Distill-Qwen-7B2026.01448.7
ACBackbone=Deepseek-R1-Distill-Qwen-7B2026.01512.2
DSCBackbone=Deepseek-R1-Distill-Qwen-7B2026.01733.5
DeepConfBackbone=Deepseek-R1-Distill-Qwen-7B2026.011,020.4