List your company

Mathematics on AIME 2024 (Score %)

90.94AIME 2024 Score (%)STEP3-VL-10B
-0.174423.480347.13570.7897Oct 7, 2025Oct 23, 2025Nov 9, 2025Nov 25, 2025Dec 12, 2025Dec 28, 2025Jan 14, 2026

Evaluation results

MethodLinks
STEP3-VL-10BNumber of Parameters=10B2026.0190.94
InternVL 3.5Number of Parameters=8B2026.0178.18
MiMo-VL RL-2508Number of Parameters=7B2026.0175.36
Qwen3-VL ThinkingNumber of Parameters=8B2026.0174.06
GLM-4.6V FlashNumber of Parameters=9B2026.0137.92
ePFBackbone=Qwen2.5-7B-In, Weighting scheme=w2025.1026.23
PFBackbone=Qwen2.5-7B-In, Weighting scheme=w2025.1026.06
Best-of-NBackbone=Qwen2.5-7B-In, Weighting scheme=w2025.1023.09
PFBackbone=Qwen2.5-7B-In, Weighting scheme=u2025.1021.6
ePFBackbone=Qwen2.5-7B-In, Weighting scheme=u2025.1021
Best-of-NBackbone=Qwen2.5-7B-In, Weighting scheme=u2025.1020.2
PFBackbone=Qwen2.5-7B-In, Weighting scheme=iw2025.1018.13
Beam-SearchBackbone=Qwen2.5-7B-In, Weighting scheme=w2025.1017.93
Best-of-NBackbone=Qwen2.5-7B-In, Weighting scheme=iw2025.1017.48
ePFBackbone=Qwen2.5-1.5B-In, Weighting scheme=w2025.1017.06
ePFBackbone=Qwen2.5-7B-In, Weighting scheme=iw2025.1016.06
Beam-SearchBackbone=Qwen2.5-7B-In, Weighting scheme=u2025.1014
Beam-SearchBackbone=Qwen2.5-7B-In, Weighting scheme=iw2025.1011.26
ePFBackbone=Qwen2.5-1.5B-In, Weighting scheme=u2025.1011.2
PFBackbone=Qwen2.5-1.5B-In, Weighting scheme=w2025.1011.16
Beam-SearchBackbone=Qwen2.5-1.5B-In, Weighting scheme=w2025.1010.29
Base SamplingBackbone=Qwen2.5-7B-In, Weighting scheme=u2025.1010
Best-of-NBackbone=Qwen2.5-1.5B-In, Weighting scheme=w2025.109.9
PFBackbone=Qwen2.5-1.5B-In, Weighting scheme=u2025.109
Beam-SearchBackbone=Qwen2.5-1.5B-In, Weighting scheme=u2025.108.4
Best-of-NBackbone=Qwen2.5-1.5B-In, Weighting scheme=u2025.107.2
PFBackbone=Qwen2.5-1.5B-In, Weighting scheme=iw2025.106.99
Beam-SearchBackbone=Qwen2.5-1.5B-In, Weighting scheme=iw2025.105.55
ePFBackbone=Qwen2.5-1.5B-In, Weighting scheme=iw2025.105.55
Best-of-NBackbone=Qwen2.5-1.5B-In, Weighting scheme=iw2025.104
Base SamplingBackbone=Qwen2.5-1.5B-In, Weighting scheme=u2025.103.33