List your company

Mathematical Reasoning on AMC23 (Accuracy and Length)

2,246Solution LengthShorterBetter
1,904.764,208.136,511.58,814.87Mar 9, 2026

Evaluation results

MethodLinks
ShorterBetterBackbone=DeepSeek-R1-Distill-Qwen-1.5B, #RL Steps=3002026.032,24666.9
ShorterBetterBackbone=DeepSeek-R1-Distill-Qwen-7B, #RL Steps=2002026.032,71986.3
LASER-DE-4096Backbone=DeepSeek-R1-Distill-Qwen-7B, #RL Steps=10002026.032,94690
Truncated Think 4kBackbone=DeepSeek-R1-Distill-Qwen-7B, #RL Steps=N/A2026.033,51145.6
Truncated Think 4kBackbone=DeepSeek-R1-Distill-Qwen-1.5B, #RL Steps=N/A2026.033,62742.5
SmartThinkerBackbone=DeepSeek-R1-Distill-Qwen-7B, #RL Steps=752026.034,11890
ThinkPrune-4kBackbone=DeepSeek-R1-Distill-Qwen-1.5B, #RL Steps=N/A2026.034,20176.3
Truncated Think 4kBackbone=Qwen3-4B-Thinking-2507, #RL Steps=N/A2026.034,31912
LASER-DE-4096Backbone=DeepSeek-R1-Distill-Qwen-1.5B, #RL Steps=10002026.034,33071.9
SmartThinkerBackbone=DeepSeek-R1-Distill-Qwen-1.5B, #RL Steps=1502026.034,42176.3
Truncated Think 8kBackbone=DeepSeek-R1-Distill-Qwen-7B, #RL Steps=N/A2026.034,65753.1
Truncated Think 8kBackbone=DeepSeek-R1-Distill-Qwen-1.5B, #RL Steps=N/A2026.035,47150.6
SmartThinkerBackbone=Qwen3-4B-Thinking-2507, #RL Steps=502026.035,99298.8
Base ModelBackbone=DeepSeek-R1-Distill-Qwen-7B, #RL Steps=N/A2026.036,63491.9
Truncated Think 8kBackbone=Qwen3-4B-Thinking-2507, #RL Steps=N/A2026.037,06715
Base ModelBackbone=DeepSeek-R1-Distill-Qwen-1.5B, #RL Steps=N/A2026.039,32073.1
Base ModelBackbone=Qwen3-4B-Thinking-2507, #RL Steps=N/A2026.0310,77799.4