List your company

Multi-Turn Problem Solving on KMP-FQA

91.2KMP-FQA ScoreGemini 2.0 Flash
48.45659.55370.6581.747Mar 3, 2026

Evaluation results

MethodLinks
Gemini 2.0 FlashSize=-2026.0391.2
Gemini 2.0 FlashSize=-2026.0391.2
LearnLM-1.5-ProSize=-2026.0387.7
LearnLM-1.5-ProSize=-2026.0387.7
Phi-4Size=14B2026.0385.6
GPT-4oSize=-2026.0384.1
GPT-4oSize=-2026.0384.1
Qwen2.5-Math-72B-InstSize=72B2026.0383.2
Qwen2.5-Math-72B-InstSize=72B2026.0383.2
Qwen2.5-32B-InstSize=32B2026.0382.6
Qwen2.5-72B-InstSize=72B2026.0382.2
Qwen2.5-72B-InstSize=72B2026.0382.2
Qwen2.5-14B-InstSize=14B2026.0381.4
GPT-4o miniSize=-2026.0379.4
GPT-4o miniSize=-2026.0379.4
KMP-LM-7BSize=7B2026.0377.5
KMP-LM-7BSize=7B2026.0377.5
Qwen2.5-Math-7B-InstSize=7B2026.0376.1
Qwen2.5-Math-7B-InstSize=7B2026.0376.1
Qwen2.5-7B-InstSize=7B2026.0371
Qwen2.5-7B-InstSize=7B2026.0371
TutorChat-LLMSize=7B2026.0357.7
TutorChat-LLMSize=7B2026.0357.7
MathChatsync-LLMSize=7B2026.0353.5
MathChatsync-LLMSize=7B2026.0353.5
Mistral-Nemo-InstSize=12B2026.0350.2
Llama-3.1-8B-InstSize=8B2026.0350.1
Llama-3.1-8B-InstSize=8B2026.0350.1