List your company

Tutoring Evaluation on Tutoring Evaluation (test)

95.4AccuracyGemini-3-Flash
39.55254.05168.5583.049May 28, 2026

Evaluation results

MethodLinks
Gemini-3-FlashAccess=Closed-source2026.0595.493.997.997.796.474.897.597.893.9
PEARL-30B (Ours)Size=30B2026.059489.396.194.488.69590.795.192.9
GPT-5.1Access=Closed-source2026.0593.484.994.894.691.1899294.691.8
DeepSeek-V3.2Access=Open-source2026.0589.876.693.791.687.557.487.593.184.7
Qwen3-235B-A22BAccess=Open-source, Size=235B2026.0589.656.395.490.275.449.981.49579.2
MiniMax-M2.1Access=Open-source2026.0589.559.59492.481.15883.893.881.5
Qwen3-30B-A3B (Baseline)Size=30B, Architecture=A3B2026.0587.963.893.189.379.15081.292.679.6
Kimi-K2-InstructAccess=Open-source2026.0583.466.787.78777.643.179.286.576.4
GLM-4.7Access=Open-source2026.0582.784.386.285.681.352.482.686.580.2
MuduoLLM-14BAccess=Open-source, Size=14B2026.055946.273.566.654.542.657.273.859.2
InnoSpark-plus-72BAccess=Open-source, Size=72B2026.0556.43767.957.640.740.945.768.851.9
InnoSpark-turbo-7BAccess=Open-source, Size=7B2026.0541.729.965.651.740.939.442.266.447.2