IFBench — cost vs performance

Best current row per canonical model in the group “accuracy · evaluator=Artificial Analysis” (334 models) against total parameters. The dashed line is the Pareto frontier: no model is both better and cheaper than a point on it.

← Leaderboard

XOutput price Input price Parameters Context Memory (est.)Scalelog linearBubblecontext params none

open / restricted weights closed Pareto frontier (9 models)bubble = context window

Frontier models 9

Pareto frontier
Model	accuracy on IFBench	Rank	total parameters	Provider	Trust
MiniMax-M3MiniMax · Open weights	82.9%	3	427B	—	Independent
MiniMax M2.7MiniMax · Open weights	75.7%	26	228.7B	—	Independent
Gemma 4 31BGoogle · Open weights	75.6%	28	31.3B	—	Independent
Gemma 4 26B A4BGoogle · Open weights	72.5%	46	25.8B	—	Independent
Qwen3.5-9BQwen · Open weights	66.7%	81	9.65B	—	Independent
LFM2.5-8B-A1BLiquid AI · Open weights	55.6%	123	8.47B	—	Independent
Qwen3.5-4BQwen · Open weights	52.0%	141	4.66B	—	Independent
LFM2.5-1.2B-InstructLiquid AI · Open weights	43.8%	175	1.17B	—	Independent
Qwen3-0.6BQwen · Open weights	23.3%	312	751.6M	—	Independent

Methodology. Points are the best current row per canonical model in comparability group 'accuracy · evaluator=Artificial Analysis'. Price = cheapest current offer across providers (the provider shown). Pareto frontier maximises the score and minimises x; exact ties are all kept. memory_estimate is an estimate (see /methodology). Only the selected comparability group is plotted; points under other configurations are not mixed in. Price = cheapest current offer across providers at the time of the last crawl. Nothing is estimated except where marked.