List your company

Code Generation on CodeForces (pass@1)

53.79pass@1Claude-Sonnet-4.5
-1.444412.895327.23541.5747Mar 6, 2026

Evaluation results

MethodLinks
Claude-Sonnet-4.5Institution=Anthropic2026.0353.79
Gemini-2.5-ProInstitution=Google2026.0352.4
ReflexiCoder-8B (Multiple)Institution=Ours, setup=full iterative reasoning-reflection setup2026.0337.68
ReflexiCoder-8B (Single)Institution=Ours, setup=single-attempt without system prompt2026.0337.34
GPT-5.1Institution=OpenAI2026.0334.7
GPT-4.1Institution=OpenAI2026.0331.37
Qwen3-8BInstitution=Alibaba2026.0323.7
DeepCoder-14B-PreviewInstitution=rLLM2026.0314.24
DeepCoder-1.5B-PreviewInstitution=rLLM2026.039.89
Qwen2.5-Coder-7B-InstructInstitution=Alibaba2026.036.39
Seed-Coder-8B-InstructInstitution=ByteDance2026.034.09
DeepSeek-Coder-7B-InstructInstitution=DeepSeek2026.032.56
CodeGemma-7B-ITInstitution=Google2026.031.88
CodeLlama-7b-InstructInstitution=Meta2026.030.68