Best Value LLM: Most Accuracy per Dollar

Ranking

The cost–accuracy frontier: each model listed scores higher than every model that costs less per question. Ordered from cheapest to most accurate.

Best value LLMs: no cheaper model scores higher
#	Model	Cost / question	Score	Cost / correct answer	Speed (tok/s)
1	Granite 4.0 MicroIBM	$0.000051	25.0%	$0.0002	38
2	gpt-oss-20bOpenAI	$0.000066	51.2%	$0.00013	103
3	Mercury 2.5Inception	$0.00011	58.2%	$0.00019	157
4	gpt-oss-120bOpenAI	$0.00013	58.8%	$0.00021	82
5	GLM 5.3 FlashZ.ai	$0.00015	67.5%	$0.00022	83
6	GPT-6 LunaOpenAI	$0.00025	72.5%	$0.00034	137
7	DeepSeek V4.1 Flash 1017DeepSeek	$0.00091	73.8%	$0.0012	57
8	GPT-6.1 SolOpenAI	$0.0029	76.2%	$0.0037	41
9	Gemini 3.8 FlashGoogle	$0.0037	82.5%	$0.0045	142
10	Gemini 4 ArgonGoogle	$0.0063	84.8%	$0.0074	69
11	Claude Opus 5.5Anthropic	$0.015	85.0%	$0.017	129

How to read this

Scores come from 80 multiple-choice questions from SuperGPQA and MMLU-Pro. With that many questions, a score has a margin of error of several points, so models a few points apart are effectively tied on accuracy; the comparison pages run a significance test for any pair. To see the top two side by side, compare Granite 4.0 Micro and gpt-oss-20b.

Speed, latency and cost are measured through OpenRouter and depend on which host serves the request; your numbers on a direct API may differ. The full procedure is on the methodology page, and the data behind this ranking can be downloaded.

Other questions

Quick answers

Which AI model gives the best accuracy for the money?

11 models sit on the frontier, from Granite 4.0 Micro ($0.000051 per question, 25.0%) to Claude Opus 5.5 ($0.015, 85.0%). Rule: The cost–accuracy frontier: each model listed scores higher than every model that costs less per question. Ordered from cheapest to most accurate.

What is the runner-up?

11 models sit on the frontier, from Granite 4.0 Micro ($0.000051 per question, 25.0%) to Claude Opus 5.5 ($0.015, 85.0%).

Which of these costs least per correct answer?

gpt-oss-20b: $0.00013 per correct answer (cost per question divided by its score).

Ranking

The cost–accuracy frontier: each model listed scores higher than every model that costs less per question. Ordered from cheapest to most accurate.

Best value LLMs: no cheaper model scores higher
#	Model	Cost / question	Score	Cost / correct answer	Speed (tok/s)
1	Granite 4.0 MicroIBM	$0.000051	25.0%	$0.0002	38
2	gpt-oss-20bOpenAI	$0.000066	51.2%	$0.00013	103
3	Mercury 2.5Inception	$0.00011	58.2%	$0.00019	157
4	gpt-oss-120bOpenAI	$0.00013	58.8%	$0.00021	82
5	GLM 5.3 FlashZ.ai	$0.00015	67.5%	$0.00022	83
6	GPT-6 LunaOpenAI	$0.00025	72.5%	$0.00034	137
7	DeepSeek V4.1 Flash 1017DeepSeek	$0.00091	73.8%	$0.0012	57
8	GPT-6.1 SolOpenAI	$0.0029	76.2%	$0.0037	41
9	Gemini 3.8 FlashGoogle	$0.0037	82.5%	$0.0045	142
10	Gemini 4 ArgonGoogle	$0.0063	84.8%	$0.0074	69
11	Claude Opus 5.5Anthropic	$0.015	85.0%	$0.017	129

How to read this

Best value LLMs: no cheaper model scores higher

Ranking

How to read this

Other questions

Quick answers

Best value LLMs: no cheaper model scores higher

Ranking

How to read this

Other questions

Quick answers