List your company

Scientific Reasoning on SciKnowEval Biology

37.08Mean@16ROSD
-0.5689.20618.9828.754May 27, 2026

Evaluation results

MethodLinks
ROSDModel Size=Qwen3-8B, Training Domain=Chemistry2026.0537.08
ROSDModel Size=Qwen3-8B, Training Domain=ToolUse2026.0537.04
GRPOModel Size=Qwen3-8B, Training Domain=Chemistry2026.0536.17
GRPOModel Size=Qwen3-8B, Training Domain=ToolUse2026.0536.13
SDPOModel Size=Qwen3-8B, Training Domain=Material2026.0535.83
SDPOModel Size=Qwen3-8B, Training Domain=ToolUse2026.0535.21
SDPOModel Size=Qwen3-8B, Training Domain=Physics2026.0534.46
ROSDModel Size=Qwen3-8B, Training Domain=Physics2026.0534.17
ROSDModel Size=Qwen3-4B, Training Domain=Physics2026.0533.88
GRPOModel Size=Qwen3-4B, Training Domain=Material2026.0533.63
SDPOModel Size=Qwen3-4B, Training Domain=Physics2026.0532.96
ROSDModel Size=Qwen3-8B, Training Domain=Material2026.0531.75
SDPOModel Size=Qwen3-4B, Training Domain=Chemistry2026.0531.54
ROSDModel Size=Qwen3-4B, Training Domain=Material2026.0531.29
GRPOModel Size=Qwen3-4B, Training Domain=ToolUse2026.0530.54
ROSDModel Size=Qwen3-4B, Training Domain=Chemistry2026.0530.5
ROSDModel Size=Qwen3-4B, Training Domain=ToolUse2026.0529.63
GRPOModel Size=Qwen3-4B, Training Domain=Chemistry2026.0528.88
GRPOModel Size=Qwen3-4B, Training Domain=Physics2026.0528.71
SDPOModel Size=Qwen3-8B, Training Domain=Chemistry2026.0528.67
SDPOModel Size=Qwen3-4B, Training Domain=Material2026.0528.46
GRPOModel Size=Qwen3-8B, Training Domain=Material2026.0527.79
GRPOModel Size=Qwen3-8B, Training Domain=Physics2026.0525.96
SDPOModel Size=Qwen3-4B, Training Domain=ToolUse2026.050.88