Aider polyglot — cost vs performance

Best current row per canonical model in the group “pass_rate_2” (61 models) against ESTIMATED memory at 4-bit, 8K context (GB). 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 (5 models)bubble = total parametersEstimated

Frontier models 5

Pareto frontier
Model	pass_rate_2 on Aider polyglot	Rank	ESTIMATED memory at 4-bit, 8K context (GB)	Provider	Trust
Kimi K2 0711Moonshot AI · Open weights	59.1%	21	590.7 GBest.	—	Official board
R1DeepSeek · Open weights	56.9%	22	394.1 GBest.	—	Official board
gpt-oss-120bOpenAI · Open weights	41.8%	36	67.7 GBest.	—	Official board
Qwen3 32BQwen · Open weights	40%	37	19.3 GBest.	—	Official board
QwQ-32BAlibaba Group · Open weights	20.9%	49	18.9 GBest.	—	Official board

Methodology. Points are the best current row per canonical model in comparability group 'pass_rate_2'. 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.