List your company

Code Input Prediction on CRUXEval-I

67.5Pass@1MiMo-V2 Flash
14.87628.53842.255.862Feb 29, 2024Jul 14, 2024Nov 27, 2024Apr 12, 2025Aug 26, 2025Jan 9, 2026May 26, 2026

Evaluation results

MethodLinks
MiMo-V2 FlashShots=1-shot, Chain-of-Thought (CoT)=true, # Total Params=309B, # Active Params=15.1B2026.0567.5—
Qwen3.5Shots=1-shot, Chain-of-Thought (CoT)=true, # Total Params=35B, # Active Params=2.6B2026.0566—
Nemotron-3-NanoShots=1-shot, Chain-of-Thought (CoT)=true, # Total Params=31.6B, # Active Params=3.6B2026.0563.2—
LAGUNA XS.2Shots=1-shot, Chain-of-Thought (CoT)=true, # Total Params=33.4B, # Active Params=3B2026.0561.9—
Gemma-4Shots=1-shot, Chain-of-Thought (CoT)=true, # Total Params=25.2B, # Active Params=3.8B2026.0554.7—
LoPAModel=DeepseekCoder-7B, #Params=6.35M2024.0550—
StarCoder2Parameters=15B2024.0248.166.9
LoRAModel=DeepseekCoder-7B, #Params=11.8M2024.0547.5—
CodeLlamaParameters=34B2024.0247.266.6
DeepSeekCoderParameters=33B2024.0246.564.9
PTModel=DeepseekCoder-7B, #Params=41.0K2024.0545.8—
LoRAModel=Llama3-8B, #Params=9.4M2024.0545.5—
FFTModel=DeepseekCoder-1.3B, #Params=1.3B2024.0545—
LoPAModel=DeepseekCoder-1.3B, #Params=4.2M2024.0543—
LoPAModel=Phi2-2.7B, #Params=4.76M2024.0543—
CodeLlamaParameters=13B2024.0242.562
LoPAModel=Phi3-3.8B, #Params=5.3M2024.0542.2—
DeepSeekCoderParameters=6.7B2024.0241.962.7
LoRAModel=Phi2-2.7B, #Params=7.9M2024.0541.5—
PTModel=DeepseekCoder-1.3B, #Params=20.5K2024.0541.2—
LoPAModel=Llama3-8B, #Params=6.4M2024.0541.2—
S-IDPGModel=DeepseekCoder-7B, #Params=32.1M2024.0540.5—
FFTModel=Phi2-2.7B, #Params=2.7B2024.0540.2—
None (Zero-shot)Model=DeepseekCoder-7B, #Params=02024.0539.3—
FFTModel=Phi3-3.8B, #Params=3.8B2024.0539.2—
LoRAModel=Phi3-3.8B, #Params=6.3M2024.0538—
PTModel=Llama3-8B, #Params=41.0K2024.0537.5—
CodeLlamaParameters=7B2024.0235.952.9
LoRAModel=DeepseekCoder-1.3B, #Params=4.7M2024.0535.5—
PTModel=Phi2-2.7B, #Params=25.6K2024.0535—
S-IDPGModel=Phi2-2.7B, #Params=20.3M2024.0535—
StarCoder2Parameters=7B2024.0234.653.5
LoPAModel=CodeGen-350M, #Params=4.4M2024.0534.5—
None (Zero-shot)Model=Phi3-3.8B, #Params=02024.0533.8—
StableCodeParameters=3B2024.0233.553.3
None (Zero-shot)Model=Phi2-2.7B, #Params=02024.0533.5—
PTModel=Phi3-3.8B, #Params=30.7K2024.0533.5—
FFTModel=CodeGen-350M, #Params=350M2024.0533—
PTModel=CodeGen-350M, #Params=10.2K2024.0532.8—
StarCoder2Parameters=3B2024.0232.750.1
StarCoderBaseParameters=15B2024.0231.349.2
LoRAModel=CodeGen-350M, #Params=1.3M2024.0531—
S-IDPGModel=Phi3-3.8B, #Params=24.2M2024.0531—
StarCoderBaseParameters=7B2024.0229.747.3
S-IDPGModel=Llama3-8B, #Params=32.1M2024.0529.2—
DeepSeekCoderParameters=1.3B2024.0227.844.7
StarCoderBaseParameters=3B2024.0227.143.7
None (Zero-shot)Model=Llama3-8B, #Params=02024.0527—
None (Zero-shot)Model=DeepseekCoder-1.3B, #Params=02024.0526.8—
S-IDPGModel=DeepseekCoder-1.3B, #Params=16.3M2024.0526—
None (Zero-shot)Model=CodeGen-350M, #Params=02024.0520.8—
S-IDPGModel=CodeGen-350M, #Params=8.5M2024.0516.9—