List your company
ResearchFormerly WizWand

Mathematical Reasoning on HMMT 2025 (held-out)

56.2AccuracyAntiSD
8.98421.24233.545.758May 12, 2026
Updated 5mo ago

Evaluation results

MethodLinks
AntiSDBackbone=Olmo3-7B-TK, Training Condition=+AntiSD, Speedup=2.0×, Peak-mean step=40, Sampling strategy=avg@322026.0556.2
AntiSDBackbone=Qwen3-30B-A3B, Training Condition=+AntiSD, Speedup=2.9×, Peak-mean step=140, Sampling strategy=avg@322026.0555.2
AntiSDBackbone=Qwen3-8B, Training Condition=+AntiSD, Speedup=5.0×, Peak-mean step=180, Sampling strategy=avg@322026.0554.4
GRPOBackbone=Olmo3-7B-TK, Training Condition=+GRPO, Speedup=1.0×, Peak-mean step=80, Sampling strategy=avg@322026.0550.5
SDBackbone=Olmo3-7B-TK, Training Condition=+SD, Peak-mean step=40, Sampling strategy=avg@322026.0548.3
Olmo3-7B-TKBackbone=Olmo3-7B-TK, Training Condition=Base, Sampling strategy=avg@322026.0548.2
AntiSDBackbone=Qwen3-4B-IT-2507, Training Condition=+AntiSD, Speedup=10.0×, Peak-mean step=100, Sampling strategy=avg@322026.0546.7
GRPOBackbone=Qwen3-30B-A3B, Training Condition=+GRPO, Speedup=1.0×, Peak-mean step=150, Sampling strategy=avg@322026.0542.2
GRPOBackbone=Qwen3-8B, Training Condition=+GRPO, Speedup=1.0×, Peak-mean step=200, Sampling strategy=avg@322026.0539.2
GRPOBackbone=Qwen3-4B-IT-2507, Training Condition=+GRPO, Speedup=1.0×, Peak-mean step=200, Sampling strategy=avg@322026.0534.1
AntiSDBackbone=Olmo3-7B-IT, Training Condition=+AntiSD, Speedup=9.5×, Peak-mean step=200, Sampling strategy=avg@322026.0532.3
GRPOBackbone=Olmo3-7B-IT, Training Condition=+GRPO, Speedup=1.0×, Peak-mean step=190, Sampling strategy=avg@322026.0531.2
Qwen3-4B-IT-2507Backbone=Qwen3-4B-IT-2507, Training Condition=Base, Sampling strategy=avg@322026.0530.4
SDBackbone=Qwen3-4B-IT-2507, Training Condition=+SD, Peak-mean step=10, Sampling strategy=avg@322026.0528.8
Olmo3-7B-ITBackbone=Olmo3-7B-IT, Training Condition=Base, Sampling strategy=avg@322026.0525.9
SDBackbone=Olmo3-7B-IT, Training Condition=+SD, Peak-mean step=10, Sampling strategy=avg@322026.0524.4
SDBackbone=Qwen3-30B-A3B, Training Condition=+SD, Peak-mean step=60, Sampling strategy=avg@322026.0520.9
SDBackbone=Qwen3-8B, Training Condition=+SD, Peak-mean step=200, Sampling strategy=avg@322026.0514.9
Qwen3-30B-A3BBackbone=Qwen3-30B-A3B, Training Condition=Base, Sampling strategy=avg@322026.0511.7
Qwen3-8BBackbone=Qwen3-8B, Training Condition=Base, Sampling strategy=avg@322026.0510.8