List your company

Scientific Reasoning on MSEarth-MCQ

65.8ScoreGemini-3-Pro
45.447250.731156.01561.2989Jan 27, 2026Feb 5, 2026Feb 15, 2026Feb 25, 2026Mar 6, 2026Mar 16, 2026Mar 26, 2026

Evaluation results

MethodLinks
Gemini-3-Pro2026.0365.8
Intern-S1-ProNumber of Parameters=1T-A22B, Thinking Configuration=false2026.0365.2
GPT-5.22026.0362.6
Kimi-K2.5Number of Parameters=1T-A32B2026.0361.9
Intern-S1variant=mini, parameters=9B2026.0156.93
InternVL3.5parameters=8B2026.0156.5
LLaVA-OVversion=1.5, parameters=8B2026.0154.81
Innovator-VLvariant=8B-Thinking, parameters=8B2026.0152.87
Qwen3-VL-235B-ThinkingNumber of Parameters=235B-A22B, Thinking Configuration=true2026.0352.7
Innovator-VLvariant=8B-Instruct, parameters=8B2026.0152.59
MiniCPM-Vversion=4.5, parameters=8B2026.0150.5
Qwen3-VLparameters=8B2026.0148.56
MiMo-VLtraining=7B-RL, parameters=7B2026.0146.66
MiMo-VLtraining=7B-SFT, parameters=7B2026.0146.23