MMMU-Pro — cost vs performance

Best current row per canonical model in the group “accuracy · evaluator=Artificial Analysis” (157 models) against cheapest current output 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 (7 models)bubble = total parameters

Frontier models 7

Pareto frontier
Model	accuracy on MMMU-Pro	Rank	cheapest current output price (USD / 1M tokens)	Provider	Trust
gpt-6-astraOpenAI · Closed	86.9%	1	$25	OpenRouter	Independent
Gemini 3.8 FlashGoogle · Closed	85.6%	2	$1.88	OpenRouter	Independent
Qwen 3.7 PlusQwen · Closed	80.5%	15	$1.28	Together AI	Independent
Qwen3.8 FlashQwen · Open weights	79.8%	20	$0.47	OpenRouter	Independent
Ling 3.0 Flash VLinclusionAI · Open weights	79.0%	24	$0.18	OpenRouter	Independent
Qwen3.5-9BQwen · Open weights	69.3%	73	$0.15	OpenRouter	Independent
Ministral 3 3BMistral AI · Open weights	38.1%	144	$0.10	Mistral AI La Plateforme	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.