List your company

Scientific Code Generation on SciCode (test)

43.8Subset AccuracyLCP
11.97620.23828.536.762Mar 3, 2026

Evaluation results

MethodLinks
LCPModel=Claude-sonnet-4, Knowledge Condition=With Knowledge2026.0343.813.8
LCPModel=Deepseek-R1, Knowledge Condition=With Knowledge2026.0343.113.8
LCPModel=Claude-sonnet-4, Knowledge Condition=Without Knowledge2026.0342.713.8
LCPModel=Deepseek-v3, Knowledge Condition=With Knowledge2026.0342.412.3
LCPModel=Qwen3-235B-A22b-Instruct, Knowledge Condition=With Knowledge2026.034110.8
LCPModel=Deepseek-R1, Knowledge Condition=Without Knowledge2026.034110.8
LCPModel=GPT-4o, Knowledge Condition=With Knowledge2026.0340.610.8
LCPModel=Deepseek-v3, Knowledge Condition=Without Knowledge2026.0340.310.8
LCPModel=Qwen3-235B-A22b-Instruct, Knowledge Condition=Without Knowledge2026.0338.99.2
BaselineModel=Deepseek-v3, Knowledge Condition=With Knowledge2026.0338.810.8
BaselineModel=Claude-sonnet-4, Knowledge Condition=With Knowledge2026.0338.810.8
LCPModel=Qwen3-next-80b a3b-instruct, Knowledge Condition=With Knowledge2026.0338.510.8
BaselineModel=Deepseek-R1, Knowledge Condition=With Knowledge2026.0337.810.8
LCPModel=Qwen3-next-80b a3b-instruct, Knowledge Condition=Without Knowledge2026.0337.59.2
BaselineModel=Qwen3-235B-A22b-Instruct, Knowledge Condition=With Knowledge2026.0337.210.8
LCPModel=GPT-4o, Knowledge Condition=Without Knowledge2026.0337.27.7
LCPModel=Qwen3-32b, Knowledge Condition=With Knowledge2026.0336.17.7
BaselineModel=GPT-4o, Knowledge Condition=With Knowledge2026.0333.77.7
LCPModel=Qwen3-32b, Knowledge Condition=Without Knowledge2026.03336.2
LCPModel=Qwen3-14b, Knowledge Condition=With Knowledge2026.0332.66.2
BaselineModel=Qwen3-next-80b a3b-instruct, Knowledge Condition=With Knowledge2026.0332.612.3
BaselineModel=Claude-sonnet-4, Knowledge Condition=Without Knowledge2026.0331.37.7
LCPModel=Qwen3-14b, Knowledge Condition=Without Knowledge2026.0330.66.2
BaselineModel=Qwen3-235B-A22b-Instruct, Knowledge Condition=Without Knowledge2026.0330.64.6
BaselineModel=Deepseek-R1, Knowledge Condition=Without Knowledge2026.0329.64.6
BaselineModel=Deepseek-v3, Knowledge Condition=Without Knowledge2026.0327.83.1
LCPModel=Qwen3-8b, Knowledge Condition=With Knowledge2026.0327.44.6
BaselineModel=Qwen3-32b, Knowledge Condition=With Knowledge2026.0327.47.7
BaselineModel=Qwen3-14b, Knowledge Condition=With Knowledge2026.03256.2
LCPModel=Qwen3-8b, Knowledge Condition=Without Knowledge2026.0324.74.6
BaselineModel=GPT-4o, Knowledge Condition=Without Knowledge2026.0324.11.5
BaselineModel=Qwen3-next-80b a3b-instruct, Knowledge Condition=Without Knowledge2026.0321.53.1
BaselineModel=Qwen3-8b, Knowledge Condition=With Knowledge2026.0319.81.5
BaselineModel=Qwen3-32b, Knowledge Condition=Without Knowledge2026.0318.40
BaselineModel=Qwen3-14b, Knowledge Condition=Without Knowledge2026.0317.71.5
BaselineModel=Qwen3-8b, Knowledge Condition=Without Knowledge2026.0313.20