modelgrep

LiquidAI: LFM2-24B-A2B vs Qwen: Qwen3 8B

LiquidAI: LFM2-24B-A2B wins on more metrics (5 of 8), but the right pick depends on what you optimize for — see the breakdown below.

MetricLiquidAI: LFM2-24B-A2BQwen: Qwen3 8B
Intelligence Index10.510.6
Coding Index3.67.1
GPQA Diamond47%45%
Design Arena Elo
Speed (tokens/sec)5330
Latency203ms656ms
Input price /M$0.030$0.050
Output price /M$0.120$0.400
Context window128K131K
CapabilitiesReasoningToolsJSON