List your company

Multimodal Mathematical Reasoning on MathVerse mini (test)

70.94T-Dominant ScoreClaude-4-Sonnet
13.490428.405243.3258.2348Jan 5, 2026Jan 10, 2026Jan 15, 2026Jan 20, 2026Jan 25, 2026Jan 30, 2026Feb 4, 2026

Evaluation results

MethodLinks
Claude-4-SonnetModel Category=Proprietary2026.0270.9449.8565.9956.9850.3852.5418.53————————
Gemini-2.5-ProModel Category=Proprietary2026.0265.2350.7656.9855.3350.7650.7631.73————————
Guided-GRPOBackbone=Qwen3-8B, Training=G-GRPO+SFT2026.0261.6851.0753.4353.9348.9848.7342.01————————
GPT-4oModel Category=Proprietary2026.0261.1748.8854.752.9246.4546.9536.93————————
Base (Qwen3-8B)Backbone=Qwen3-8B2026.0258.3846.8347.0848.645.0544.4237.69————————
Vision-R1-32BModel Category=Open-Source2026.0257.7450.6649.8753.055048.643.91————————
MMR1-32BModel Category=Open-Source2026.0254.9546.3547.3446.9545.1844.0440.61————————
GPT-4V2026.0154.7—48.741.434.934.431.639.454.463.156.660.351.450.850.3
VL-Rethinker-7BModel Category=Open-Source2026.0254.4447.6648.3550.3845.9445.5642.01————————
MathFlow GPT-4V2026.0151.1—48.546.440.337.43943.856.765.258.962.153.752.152.5
Qwen-VL-MaxModel Category=Proprietary2026.0248.9835.9128.9339.4730.0830.0830.94————————
Math-LLaVA-13BModel Category=Open-Source2026.0248.9833.6831.4739.8528.0527.6623.86————————
LLaVA-v1.5-13BModel Category=Open-Source2026.0248.2235.4834.7739.4736.0434.1419.54————————
Qwen2.5-VL-32BModel Category=Open-Source2026.0244.2938.8845.1839.9739.0940.130.96————————
InternVL2.5-26BModel Category=Open-Source2026.0243.939.3441.538.7141.541.3731.22————————
COGFLOW-7BParameters=7B2026.0141.9—40.13742.444.826.339.553.960.751.252.35558.744.2
SVE-Math-Qwen2.5-7BBackbone=Qwen2.5, Parameters=7B2026.0137.6——36.834.931.51631.4———————
MultiMath-7BParameters=7B2026.0134.8——30.828.125.91526.9———————
Qwen-VL-Max2026.0130.7—28.926.124.124.121.425.337.242.837.747.933.635.935.9
Llama-3.2-11BModel Category=Open-Source2026.0227.1624.2925.7624.8724.8724.4920.05————————
Gemini-Pro2026.0126.3—27.323.52322.322.223.535.339.834.744.53236.833.3
Phi-3-vision-128kModel Category=Open-Source2026.0222.9717.4620.0517.6417.2615.8613.58————————
Math-LLaVA-13BParameters=13B2026.0122.8——21.821.119.215.420.1———————
InternLM-XC2-7BParameters=7B2026.0122.3—16.51715.716.41116.525.936.928.342.520.124.419.8
SPHINX-MoE-56BParameters=56B2026.0122.2—18.316.414.812.69.115.625.833.321.940.721.119.618.3
Qwen-VL-Plus2026.0115.7—14.511.19131011.821.32621.225.218.519.121.8
DVLR-14BParameters=14B2026.01————————48.154.349—46.347.243.8
GRPOModel=Qwen2.5-VL-3B, Paradigm=GRPO2026.02———————48.67———————
GRPOModel=Qwen2.5-VL-7B, Paradigm=GRPO2026.02———————57.16———————
Qwen2.5-VL-7BBackbone=Qwen2.5-VL-7B2026.01———————44.8———————
SFTModel=Qwen2.5-VL-3B, Paradigm=SFT2026.02———————49.54———————
SFTModel=Qwen2.5-VL-7B, Paradigm=SFT2026.02———————58.39———————
SFT-MModel=Qwen2.5-VL-3B, Paradigm=SFT-M2026.02———————51.51———————
SFT-MModel=Qwen2.5-VL-7B, Paradigm=SFT-M2026.02———————59.31———————
SFT-RSModel=Qwen2.5-VL-3B, Paradigm=SFT-RS2026.02———————48.72———————
SFT-RSModel=Qwen2.5-VL-7B, Paradigm=SFT-RS2026.02———————55.87———————
SophiaVL-R1-7BParameters=7B2026.01————————48.845.443.9—45.158.551.3
VideoAuto-R1Backbone=Qwen2.5-VL-7B2026.01———————46.9———————