Design Composite Index

BudgetMeta

Max

58.1score
$0.029/ task
Best valueOpenAI

Max

72.9score
$2.18/ task
Top scoreAnthropic

Extra high

81.1score
$24.7/ task
Design score versus cost Pareto frontierScoreCost / task (log)2030405060708090$0.03$0.06$0.2$0.4$0.7$2$4$7$20
Use Left, Right, Home, and End keys to compare qualifying models across spend caps, or Escape to clear.
ModelProviderScoreCost / taskInput / output ($/1M)
Anthropic81.1$24.7$8.00 / $40
Anthropic80.6$24.7$4.00 / $20
Anthropic75.1$19.8$2.00 / $10
Google74.6$8.33$2.00 / $10
OpenAI74.3$8.70$8.00 / $40
Google74.2$8.05$3.00 / $15
OpenAI72.9$2.18$2.00 / $10
Anthropic70.5$12.6$8.00 / $40
Meta69.8$1.13$1.25 / $4.25
Meta68.5$1.12$4.00 / $20
Google67.2$2.36$1.50 / $7.50
Anthropic66.0$10.1$2.00 / $10
OpenAI63.4$1.69$2.00 / $10
Meta60.6$0.81$1.25 / $4.25
SpaceXAI59.3$15.9$2.00 / $6.00
Meta58.1$0.029$0.10 / $0.50
SpaceXAI57.4$2.55$2.00 / $6.00
Google54.6$1.59$0.75 / $3.75
OpenAI54.3$0.68$0.10 / $0.50
Anthropic54.2$5.98$0.10 / $0.50
Anthropic53.5$3.05$0.10 / $0.50
SpaceXAI50.7$2.15$2.00 / $6.00
OpenAI50.1$0.37$0.20 / $1.20
Google44.6$1.36$1.50 / $9.00
Google41.7$0.83$1.50 / $9.00
Google36.4$0.44$0.30 / $2.50
SpaceXAI28.5$0.43$1.25 / $2.50