All AI models compared: benchmarks and prices

Model	Humanity's Last Exam	Per task	Price	Speed	Context
LFM2.5 8B A1BLiquid AIOpen	6.9thinking	—		—	128K
LFM2.5 1.2B InstructLiquid AIOpen	6.7non-thinking	—		—	33K
LFM2.5 1.2B ThinkingLiquid AIOpen	6.2thinking	—		—	33K
LFM2 1.2BLiquid AIOpen	5.6	—		—	33K
LFM2 2.6BLiquid AIOpen	5.5	—		—	33K
LFM2.5 VL 1.6BLiquid AIOpen	5.1non-thinking	—		—	33K
LFM2 8B A1BLiquid AIOpen	4.9	—		—	33K
LFM2 24B A2BLiquid AIOpen	4.2non-thinking	—	$0.03 / $0.12	—	33K