List your company

Mathematical Reasoning on AIME24 (Pass@1 Avg@16)

51.3Pass@1 (Avg@16)DLER-R1-7B-Research
17.91626.58335.2543.917Jan 31, 2026

Evaluation results

MethodLinks
DLER-R1-7B-ResearchBackbone=DeepSeek-R1-Distill-Qwen-7B, Sampling Temperature=0.6, Max Response Length=8192, Rollout samples=162026.0151.33,2091.6
Laser-DE-L4096-7BBackbone=DeepSeek-R1-Distill-Qwen-7B, Sampling Temperature=0.6, Max Response Length=8192, Rollout samples=162026.0147.74,6421.1
AdaptThink-7B-delta0.05Backbone=DeepSeek-R1-Distill-Qwen-7B, Sampling Temperature=0.6, Max Response Length=8192, Rollout samples=162026.0145.66,2550.7
SB DS7B alpha 2Backbone=DeepSeek-R1-Distill-Qwen-7B, Sampling Temperature=0.6, Max Response Length=8192, Rollout samples=162026.0145.43,9551.02
L1-Qwen-7B-MaxBackbone=DeepSeek-R1-Distill-Qwen-7B, Sampling Temperature=0.6, Max Response Length=8192, Rollout samples=162026.0144.84,0410.96
APR-7B (Ours)Backbone=DeepSeek-R1-Distill-Qwen-7B, Sampling Temperature=0.6, Max Response Length=8192, Rollout samples=162026.01443,0511.04
TrainingEfficient DS-7BBackbone=DeepSeek-R1-Distill-Qwen-7B, Sampling Temperature=0.6, Max Response Length=8192, Rollout samples=162026.0142.16,2300.42
Original ModelBackbone=DeepSeek-R1-Distill-Qwen-7B, Sampling Temperature=0.6, Max Response Length=8192, Rollout samples=162026.0137.76,707—
DLER-R1-1.5B-ResearchBackbone=DeepSeek-R1-Distill-Qwen-1.5B, Sampling Temperature=0.6, Max Response Length=8192, Rollout samples=162026.0132.13,3762.55
DS-1.5B-thinkprune-iter2kBackbone=DeepSeek-R1-Distill-Qwen-1.5B, Sampling Temperature=0.6, Max Response Length=8192, Rollout samples=162026.01304,6702.05
TrainingEfficient DS-1.5BBackbone=DeepSeek-R1-Distill-Qwen-1.5B, Sampling Temperature=0.6, Max Response Length=8192, Rollout samples=162026.0129.26,2451.7
APR-1.5B (Ours)Backbone=DeepSeek-R1-Distill-Qwen-1.5B, Sampling Temperature=0.6, Max Response Length=8192, Rollout samples=162026.01293,7672.01
L1-Qwen-1.5B-MaxBackbone=DeepSeek-R1-Distill-Qwen-1.5B, Sampling Temperature=0.6, Max Response Length=8192, Rollout samples=162026.0128.82,8932.1
Laser-L8192-1.5BBackbone=DeepSeek-R1-Distill-Qwen-1.5B, Sampling Temperature=0.6, Max Response Length=8192, Rollout samples=162026.0127.36,1391.42
AdaptThink-1.5B-delta0.05Backbone=DeepSeek-R1-Distill-Qwen-1.5B, Sampling Temperature=0.6, Max Response Length=8192, Rollout samples=162026.0126.26,1721.25
Laser-DE-L4096-1.5BBackbone=DeepSeek-R1-Distill-Qwen-1.5B, Sampling Temperature=0.6, Max Response Length=8192, Rollout samples=162026.0125.65,1731.29
Original ModelBackbone=DeepSeek-R1-Distill-Qwen-1.5B, Sampling Temperature=0.6, Max Response Length=8192, Rollout samples=162026.0119.27,278—