List your company

Accuracy on AMC Math Reasoning

80AccuracyLLM-J
-1.74419.47840.761.922Oct 5, 2025Oct 30, 2025Nov 25, 2025Dec 21, 2025Jan 16, 2026Feb 11, 2026Mar 9, 2026

Evaluation results

MethodLinks
LLM-JBackbone=GPT-OSS-120B2025.1180
LLM-JBackbone=GPT-OSS-120B2025.1180
LLM-JBackbone=Gemma-3-27B2025.1173.3
LLM-JBackbone=Gemma-3-27B2025.1173.3
APRMBackbone=GPT-OSS-120B2025.1170.7
APRMBackbone=GPT-OSS-120B2025.1170.7
Hard Neg.Backbone=GPT-OSS-120B2025.1168.5
APRMBackbone=GPT-OSS-20B2025.1168
APRMBackbone=GPT-OSS-20B2025.1168
ReST-MCTSBackbone=GPT-OSS-120B2025.1167.4
ReST-MCTSBackbone=GPT-OSS-120B2025.1167.4
rStar MathBackbone=GPT-OSS-120B2025.1167
ToTBackbone=GPT-OSS-120B2025.1166.7
ToTBackbone=GPT-OSS-20B2025.1166.7
ToTBackbone=GPT-OSS-120B2025.1166.7
ToTBackbone=GPT-OSS-20B2025.1166.7
ReST-MCTSBackbone=GPT-OSS-20B2025.1166
ReST-MCTSBackbone=GPT-OSS-20B2025.1166
rStar MathBackbone=GPT-OSS-20B2025.1165.5
AutoPSVBackbone=GPT-OSS-120B2025.1165
ARMBackbone=GPT-OSS-120B2025.1163.3
Math S.Backbone=GPT-OSS-120B2025.1162
ReST-MCTSBackbone=Gemma-3-27B2025.1161.2
ReST-MCTSBackbone=Gemma-3-27B2025.1161.2
Verify SbS.Backbone=GPT-OSS-120B2025.1161
APRMBackbone=Gemma-3-27B2025.1160.8
APRMBackbone=Gemma-3-27B2025.1160.8
rStar MathBackbone=Gemma-3-27B2025.1160.5
CoT-SCBackbone=GPT-OSS-120B2025.1160
LLM-JBackbone=GPT-OSS-20B2025.1160
ToTBackbone=Gemma-3-27B2025.1160
Hard Neg.Backbone=Gemma-3-27B2025.1160
CoT-SCBackbone=GPT-OSS-120B2025.1160
LLM-JBackbone=GPT-OSS-20B2025.1160
ToTBackbone=Gemma-3-27B2025.1160
AutoPSVBackbone=GPT-OSS-20B2025.1150
Math S.Backbone=GPT-OSS-20B2025.1148
Verify SbS.Backbone=GPT-OSS-20B2025.1145
AutoPSVBackbone=Gemma-3-27B2025.1140
AutoMRBackbone=Qwen, Skeleton Structure=DAG2025.1038.6
Meta-ReasonerBackbone=Qwen, Skeleton Structure=Sequential2025.1036.1
HILAType=MA, Backbone=LLaMA3-8B2026.0335.83
Math S.Backbone=Gemma-3-27B2025.1135
CoTBackbone=Qwen, Skeleton Structure=Sequential2025.1034.9
MRPBackbone=Qwen, Skeleton Structure=-2025.1033.7
MaASBackbone=Qwen, Skeleton Structure=Sequential2025.1033.7
CoT-SCBackbone=GPT-OSS-20B2025.1133.3
CoT-SCBackbone=GPT-OSS-20B2025.1133.3
rStarBackbone=Qwen, Skeleton Structure=Tree2025.1032.5
AutoMRBackbone=LLaMA, Skeleton Structure=DAG2025.1030.1
ARMBackbone=Gemma-3-27B2025.1130
Verify SbS.Backbone=Gemma-3-27B2025.1130
Meta-ReasonerBackbone=LLaMA, Skeleton Structure=Sequential2025.1026.5
MRPBackbone=LLaMA, Skeleton Structure=-2025.1025.3
MaASBackbone=LLaMA, Skeleton Structure=Sequential2025.1024.1
CoT-SCBackbone=Gemma-3-12B2025.1123.3
CoT-SCBackbone=Gemma-3-12B2025.1123.3
APRMBackbone=Gemma-3-12B2025.1121.6
APRMBackbone=Gemma-3-12B2025.1121.6
CoTBackbone=LLaMA, Skeleton Structure=Sequential2025.1021.2
G-DebateType=MA, Backbone=LLaMA3-8B2026.0320.48
ReST-MCTSBackbone=Gemma-3-12B2025.1120.2
ReST-MCTSBackbone=Gemma-3-12B2025.1120.2
AutoPSVBackbone=Gemma-3-12B2025.1120.1
Math S.Backbone=Gemma-3-12B2025.1120.1
rStar MathBackbone=Gemma-3-12B2025.1120.1
Verify SbS.Backbone=Gemma-3-12B2025.1120.05
LLM-JBackbone=Gemma-3-12B2025.1120
ToTBackbone=Gemma-3-12B2025.1120
LLM-JBackbone=Gemma-3-12B2025.1120
ToTBackbone=Gemma-3-12B2025.1120
DyLANType=MA, Backbone=LLaMA3-8B2026.0319.68
DebateType=MA, Backbone=LLaMA3-8B2026.0319.28
A-PruneType=MA, Backbone=LLaMA3-8B2026.0316.47
rStarBackbone=LLaMA, Skeleton Structure=Tree2025.1015.7
PHPType=MA, Backbone=LLaMA3-8B2026.0315.66
G-SwarmType=MA, Backbone=LLaMA3-8B2026.0315.66
CoT-SCBackbone=Gemma-3-27B2025.1113.3
CoT-SCBackbone=Gemma-3-27B2025.1113.3
SCType=SA, Backbone=LLaMA3-8B2026.0312.45
AFlowType=MA, Backbone=LLaMA3-8B2026.0312.05
Direct-I/OBackbone=LLaMA, Skeleton Structure=-2025.1012
CoTType=SA, Backbone=LLaMA3-8B2026.0311.65
Direct-I/OBackbone=Qwen, Skeleton Structure=-2025.108.4
VanillaType=SA, Backbone=LLaMA3-8B2026.038.03
CoScale-RL2026.017.6
COMPASS2026.016.8
SpeedControl2026.015.5
GRPO2026.015.1
SAPO2026.015.1
Scale-RL2026.014
Pretrain + RL2026.012.7
SFTed (w/o Data Scaling)Data Scaling=No2026.012.3
Qwen2.5-0.5B Instruct2026.012.1
SFTed (w/ Data Scaling)Data Scaling=Yes2026.011.4