Terminal-Bench — cost vs performance

Best current row per canonical model in the group “accuracy · variant=v4.0 · evaluator=Artificial Analysis” (114 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 (6 models)bubble = context window

Frontier models 6

Pareto frontier
Model	accuracy on Terminal-Bench	Rank	cheapest current input price (USD / 1M tokens)	Provider	Trust
gpt-6-astraOpenAI · Closed	59.6%	1	$5	OpenRouter	Independent
Claude Opus 5Anthropic · Closed	49.0%	3	$2.5	OpenRouter	Independent
GLM 5.3Z.ai (Zhipu AI) · Open weights	41.9%	5	$0.70	OpenRouter	Independent
GLM 5.3 FlashZ.ai (Zhipu AI) · Open weights	32.8%	9	$0.075	OpenRouter	Independent
NVIDIA Nemotron 3.5 Lightning 30B A3BNVIDIA · Open weights	0.51%	49	$0.05	Fireworks AI	Independent
gpt-oss-20bOpenAI · Open weights	0%	60	$0.03	OpenAI API	Independent

Methodology. Points are the best current row per canonical model in comparability group 'accuracy · variant=v4.0 · 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.