List your company

Coding Question Answering on CodeQA

62.1AccuracyRLM
5.21219.98134.7549.519Mar 20, 2026

Evaluation results

MethodLinks
RLMParadigm=P2, Model Family=Llama, Model Scale=405B2026.0362.1
RLMParadigm=P2, Model Family=Qwen3, Model Scale=235B2026.0358.6
λ-RLMParadigm=P3, Model Family=Llama, Model Scale=405B2026.0355.7
λ-RLMParadigm=P3, Model Family=Qwen3, Model Scale=235B2026.0354.2
RLMParadigm=P2, Model Family=Mistral, Model Scale=Cdsrl2026.0349.3
λ-RLMParadigm=P3, Model Family=Qwen3, Model Scale=32B2026.0347.1
RLMParadigm=P2, Model Family=Llama, Model Scale=70B2026.0346.4
λ-RLMParadigm=P3, Model Family=Mistral, Model Scale=Cdsrl2026.0344.8
λ-RLMParadigm=P3, Model Family=Llama, Model Scale=70B2026.0343.8
λ-RLMParadigm=P3, Model Family=Mistral, Model Scale=8x22B2026.0342.5
RLMParadigm=P2, Model Family=Qwen3, Model Scale=32B2026.0336.8
λ-RLMParadigm=P3, Model Family=Qwen3, Model Scale=8B2026.0335.2
λ-RLMParadigm=P3, Model Family=Llama, Model Scale=8B2026.0332.8
RLMParadigm=P2, Model Family=Mistral, Model Scale=8x22B2026.0332.4
λ-RLMParadigm=P3, Model Family=Mistral, Model Scale=7B2026.0327.6
DirectParadigm=P1, Model Family=Llama, Model Scale=405B2026.0326.3
DirectParadigm=P1, Model Family=Qwen3, Model Scale=235B2026.0324
DirectParadigm=P1, Model Family=Llama, Model Scale=70B2026.0322.1
DirectParadigm=P1, Model Family=Mistral, Model Scale=Cdsrl2026.0321.2
DirectParadigm=P1, Model Family=Qwen3, Model Scale=32B2026.0320.4
DirectParadigm=P1, Model Family=Mistral, Model Scale=8x22B2026.0318.6
RLMParadigm=P2, Model Family=Qwen3, Model Scale=8B2026.0318.5
RLMParadigm=P2, Model Family=Llama, Model Scale=8B2026.0316.7
RLMParadigm=P2, Model Family=Mistral, Model Scale=7B2026.0312.3
DirectParadigm=P1, Model Family=Llama, Model Scale=8B2026.039.2
DirectParadigm=P1, Model Family=Qwen3, Model Scale=8B2026.038.7
DirectParadigm=P1, Model Family=Mistral, Model Scale=7B2026.037.4