List your company

Code Generation on HumanEval and MBPP EvalPlus

70.1HumanEval+ Pass@kMistral-7B-Instruct-v0.2
13.6828.327542.97557.6225May 6, 2024Jun 25, 2024Aug 14, 2024Oct 3, 2024Nov 22, 2024Jan 11, 2025Mar 3, 2025

Evaluation results

MethodLinks
Mistral-7B-Instruct-v0.2Size=7B, Version=v0.2, Mode=Instruct2024.0570.17544.73759.953.6
MAmmoTH2-7B-PlusSize=7B2024.0565.972.160.150.466.158.2
DeRS-SMMoE Model=Coder-MoE [6], Added Params.=0.81B+325M2025.0362.866.563.451.461—
DeRS-LMMoE Model=Coder-MoE [6], Added Params.=0.81B+9.09M2025.0362.865.962.951.960.9—
Vanilla UpcyclingMoE Model=Coder-MoE [6], Added Params.=0.81B+2.43B2025.036164.663.951.460.2—
MAmmoTH2-8B-PlusSize=8B2024.0557.963.460.448.661.953.3
Llama-3-8B-InstructSize=8B, Mode=Instruct2024.0556.761.670.159.365.958
MAmmoTH2-8×7B-PlusSize=8x7B2024.0553.757.968.756.963.355.3
SFTModel=Phi3-mini-3.8B2025.0251.83——48.68——
Mixtral-8×7B-Instruct-v0.1Size=8x7B, Version=v0.1, Mode=Instruct2024.0539.645.159.549.752.344.7
SFTModel=Qwen2-7B2025.0239.02——39.42——
Gemma-1.1-7B-InstructSize=7B, Version=1.1, Mode=Instruct2024.0535.442.757.14549.940.2
SFTModel=Llama-3-8B2025.0234.76——50.26——
Llama-3-8BSize=8B2024.0529.333.561.451.647.540.5
SFTModel=Gemma-2-9B2025.0224.39——27.51——
Mistral-7BSize=7B2024.0523.828.751.942.140.333
CDMStudent=Gemma-2-2B, Teacher=Llama-3-8B, Category=Cross Tokenizer KD2025.0223.78——21.69——
SFTModel=Gemma-2-2B2025.0221.34——21.34——
RKLStudent=Qwen2-0.5B, Teacher=Qwen2-7B, Category=Same Tokenizer KD2025.0220.73——22.75——
ULDStudent=Gemma-2-2B, Teacher=Llama-3-8B, Category=Cross Tokenizer KD2025.0220.4——17.7——
MinEDStudent=Gemma-2-2B, Teacher=Llama-3-8B, Category=Cross Tokenizer KD2025.0220.12——22.22——
Gemma-7BSize=7B2024.0520.126.852.643.439.731.8
FKLStudent=Gemma-2-2B, Teacher=Gemma-2-9B, Category=Same Tokenizer KD2025.0218.9——23——
RKLStudent=Gemma-2-2B, Teacher=Gemma-2-9B, Category=Same Tokenizer KD2025.0218.9——21.42——
CDMStudent=Qwen2-0.5B, Teacher=Phi3-mini-3.8B, Category=Cross Tokenizer KD2025.0218.9——23.81——
MinEDStudent=Qwen2-0.5B, Teacher=Phi3-mini-3.8B, Category=Cross Tokenizer KD2025.0217.1——22.2——
FKLStudent=Qwen2-0.5B, Teacher=Qwen2-7B, Category=Same Tokenizer KD2025.0217.07——23.38——
ULDStudent=Qwen2-0.5B, Teacher=Phi3-mini-3.8B, Category=Cross Tokenizer KD2025.0217.07——22.49——
SFTModel=Qwen2-0.5B2025.0215.85——22.22——
Forward KL2026.05————46.76—
Forward KL + Ours2026.05————47.89—
Hard KD2026.05————44.66—
Reverse KL2026.05————46.34—
Reverse KL + Ours2026.05————46.82—
Skew FKL2026.05————47.29—
Skew FKL + Ours2026.05————47.92—
Skew RKL2026.05————47.31—
Skew RKL + Ours2026.05————47.68—
Student (No Distill)2026.05————42.26—
Teacher2026.05————72.56—
Total Variation2026.05————46.54—
Total Variation + Ours2026.05————47.06—
α-β divergence2026.05————47.09—
α-β divergence + Ours2026.05————49.74—