MMMU-Pro — cost vs performance

Best current row per canonical model in the group “accuracy · evaluator=Artificial Analysis” (157 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 (8 models)bubble = context window

Frontier models 8

Pareto frontier
Model	accuracy on MMMU-Pro	Rank	cheapest current input price (USD / 1M tokens)	Provider	Trust
gpt-6-astraOpenAI · Closed	86.9%	1	$5	OpenAI API	Independent
Gemini 3.8 FlashGoogle · Closed	85.6%	2	$0.375	OpenRouter	Independent
Qwen 3.7 PlusQwen · Closed	80.5%	15	$0.32	OpenRouter	Independent
Gemini 3 Flash PreviewGoogle · Closed	79.9%	18	$0.25	OpenRouter	Independent
Qwen3.8 FlashQwen · Open weights	79.8%	20	$0.15	OpenRouter	Independent
Ling 3.0 Flash VLinclusionAI · Open weights	79.0%	24	$0.06	OpenRouter	Independent
Gemma 4 26B A4BGoogle · Open weights	69.3%	73	$0.042	Google Gemini API	Independent
gpt-5-nanoOpenAI · Closed	61.0%	108	$0.025	OpenAI API	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.