List your company

Coding Reasoning on Pancreas (test)

39.28Success RateCodeCytos + Few Shot
-1.16569.334719.83530.3353May 30, 2026

Evaluation results

MethodLinks
CodeCytos + Few ShotBackbone=Qwen3-Coder-30B-A3B-Instruct, Framework=CodeAct-based, Prompting Strategy=Few Shot2026.0539.2860.1864.8664.7657
CodeCytos + One ShotBackbone=Qwen3-Coder-30B-A3B-Instruct, Framework=CodeAct-based, Prompting Strategy=One Shot2026.0533.6758.562.7962.9355
CodeCytos + Few ShotBackbone=Qwen2.5-Coder-32B-Instruct, Framework=CodeAct-based, Prompting Strategy=Few Shot2026.0532.4457.2260.3260.4153
CodeCytos + Few ShotBackbone=Facebook CWM, Framework=CodeAct-based, Prompting Strategy=Few Shot2026.0527.153.1854.6954.749
CodeCytos + One ShotBackbone=Facebook CWM, Framework=CodeAct-based, Prompting Strategy=One Shot2026.0523.6550.4957.1657.3346
CodeCytosBackbone=Qwen3-Coder-30B-A3B-Instruct, Framework=CodeAct-based, Prompting Strategy=Base2026.0517.6241.5846.5746.5238
CodeCytosBackbone=Facebook CWM, Framework=CodeAct-based, Prompting Strategy=Base2026.0514.494351.0251.0338
Tool-Augmented LLM (Without CoT)Backbone=Qwen2.5-Coder-32B-Instruct, Framework=Conventional, Prompting Strategy=Without CoT2026.054.0215.1420.1520.0313
Tool-Augmented LLM (Zero-Shot CoT)Backbone=Qwen2.5-Coder-32B-Instruct, Framework=With, Prompting Strategy=Zero-Shot CoT2026.054.0114.1818.2618.2813
Tool-Augmented LLM (Few-Shot CoT)Backbone=Qwen2.5-Coder-32B-Instruct, Framework=With, Prompting Strategy=Few-Shot CoT2026.053.7814.8520.7620.813
Tool-Augmented LLM (Without CoT)Backbone=Qwen3-Coder-30B-A3B-Instruct, Framework=Conventional, Prompting Strategy=Without CoT2026.051.265.648.148.175
Tool-Augmented LLM (Without CoT)Backbone=Facebook CWM, Framework=Conventional, Prompting Strategy=Without CoT2026.051.195.27.587.575
Tool-Augmented LLM (Few-Shot CoT)Backbone=Qwen3-Coder-30B-A3B-Instruct, Framework=With, Prompting Strategy=Few-Shot CoT2026.051.185.27.567.565
Tool-Augmented LLM (Zero-Shot CoT)Backbone=Facebook CWM, Framework=With, Prompting Strategy=Zero-Shot CoT2026.050.712.063.315.033
CodeCytos + One ShotBackbone=Qwen2.5-Coder-32B-Instruct, Framework=CodeAct-based, Prompting Strategy=One Shot2026.050.632.693.753.752
CodeCytosBackbone=Qwen2.5-Coder-32B-Instruct, Framework=CodeAct-based, Prompting Strategy=Base2026.050.623.165.045.013
Tool-Augmented LLM (Zero-Shot CoT)Backbone=Qwen3-Coder-30B-A3B-Instruct, Framework=With, Prompting Strategy=Zero-Shot CoT2026.050.52.233.163.162
Tool-Augmented LLM (Few-Shot CoT)Backbone=Facebook CWM, Framework=With, Prompting Strategy=Few-Shot CoT2026.050.391.181.973.142