IFBench — cost vs performance

Best current row per canonical model in the group “accuracy · evaluator=Artificial Analysis” (334 models) against cheapest current input price (USD / 1M tokens). 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	cheapest current input price (USD / 1M tokens)	Provider	Trust
Grok 4.3xAI · Closed	83.3%	1	$1	OpenRouter	Independent
MiniMax-M3MiniMax · Open weights	82.9%	3	$0.30	OpenRouter	Independent
Gemini 3 Flash PreviewGoogle · Closed	78.0%	12	$0.25	OpenRouter	Independent
gpt-5.4-nanoOpenAI · Closed	75.9%	23	$0.10	OpenAI API	Independent
Gemma 4 31BGoogle · Open weights	75.6%	28	$0.09	OpenRouter	Independent
Gemma 4 26B A4BGoogle · Open weights	72.5%	46	$0.042	Google Gemini API	Independent
gpt-oss-120bOpenAI · Open weights	69.0%	67	$0.037	OpenRouter	Independent
gpt-5-nanoOpenAI · Closed	67.5%	75	$0.025	OpenRouter	Independent
Granite 4.0 MicroIBM · Open weights	24.8%	305	$0.017	OpenRouter	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.