List your company

Mathematical Reasoning on MATH 500 (∆Acc, CR)

100Completion RateVanilla
24.0843.7963.583.21Apr 8, 2026

Evaluation results

MethodLinks
VanillaAccess=—, Base Model=Qwen3-14B (DEER) / Qwen3-8B-Think (ours)2026.04100—
VanillaAccess=—, Base Model=QwQ-32B (DEER) / Qwen3-32B-Think (ours)2026.04100—
Dynasor-CoTAccess=black-box, Base Model=Qwen3-14B (DEER) / Qwen3-8B-Think (ours)2026.04720.2
DEER-PRoAccess=semi-white, Base Model=QwQ-32B (DEER) / Qwen3-32B-Think (ours)2026.04721
DEERAccess=semi-white, Base Model=QwQ-32B (DEER) / Qwen3-32B-Think (ours)2026.04690.5
TCCAccess=black-box, Base Model=Qwen3-14B (DEER) / Qwen3-8B-Think (ours)2026.04610.6
DEER-PRoAccess=semi-white, Base Model=Qwen3-14B (DEER) / Qwen3-8B-Think (ours)2026.04452.8
DEERAccess=semi-white, Base Model=Qwen3-14B (DEER) / Qwen3-8B-Think (ours)2026.04410.5
BAEEAccess=black-box, Base Model=Qwen3-14B (DEER) / Qwen3-8B-Think (ours)2026.04324.4
BAEEAccess=black-box, Base Model=QwQ-32B (DEER) / Qwen3-32B-Think (ours)2026.04283
NoThinkingAccess=black-box, Base Model=Qwen3-14B (DEER) / Qwen3-8B-Think (ours)2026.04275.6