Model compare
Stormwind Trebuchet Simulator
Compare the same prompt across DeepSeek V4 Flash, GPT-5.6 Sol, MiniMax M3.
Missing runs for KimiK3 on this benchmark.
DeepSeek
DeepSeek V4 Flash
OpenAI
GPT-5.6 Sol
MiniMax
Model compare
Compare the same prompt across DeepSeek V4 Flash, GPT-5.6 Sol, MiniMax M3.
Missing runs for KimiK3 on this benchmark.
DeepSeek
OpenAI
MiniMax