AI Models Leaderboard 2026

Compare the best AI models, LLM APIs, pricing, context windows, and performance benchmarks updated dynamically.

Model	Intelligence	MMLU Pro	Context	GPQA	TTFT (s)	Speed (T/s)	Input Price (1M)	Output Price (1M)
Motif-2-12.7B-Reasoning Motif Technologies	19.1	79.6%	33K	69.5%	-	-	$0.00	$0.00
Sonar Reasoning Perplexity	17.9	-	128K	62.3%	-	-	$0.00	$0.00
DBRX Instruct Databricks	8.3	39.7%	33K	33.1%	-	-	$0.00	$0.00
Mistral: Mixtral 8x7B Instruct mistralai	7.7	38.7%	33K	29.2%	-	-	$0.54	$0.60
Mistral: Mixtral 8x22B Instruct mistralai	-	-	66K	-	-	-	$2.00	$6.00
Mistral: Mistral 7B Instruct mistralai	7.4	24.5%	33K	17.7%	0.29	145	$0.25	$0.25
Mistral: Mistral 7B Instruct v0.1 mistralai	-	-	3K	-	-	-	$0.11	$0.19
Command-R (Mar '24) Cohere	7.4	33.8%	128K	28.4%	-	-	$0.50	$1.50
Llama 65B Meta	4.0	-	2K	-	-	-	$0.00	$0.00
Qwen1.5 Chat 110B Alibaba	9.5	-	33K	28.9%	-	-	$0.00	$0.00
Qwen2 Instruct 72B Alibaba	11.7	62.2%	33K	37.1%	-	-	$0.00	$0.00
Qwen2.5 Coder Instruct 32B Alibaba	12.9	63.5%	33K	41.7%	-	-	$0.20	$0.20
Qwen2.5 Instruct 32B Alibaba	13.2	69.7%	33K	46.6%	-	-	$0.00	$0.00
Qwen2.5 Coder Instruct 7B Alibaba	10.0	47.3%	33K	33.9%	-	-	$0.00	$0.00
Qwen: Qwen2.5 VL 32B Instruct qwen	-	-	128K	-	-	-	$0.20	$0.60
Qwen2.5 Coder 32B Instruct qwen	-	-	33K	-	-	-	$0.20	$0.20
Mistral Large mistralai	9.9	51.5%	128K	35.1%	-	-	$4.00	$12.00
DeepSeek-V2-Chat DeepSeek	9.1	-	128K	-	-	-	$0.00	$0.00
R1 1776 Perplexity	12.0	-	164K	-	-	-	$0.00	$0.00
MiniMax M1 40k MiniMax	20.9	80.8%	197K	68.2%	-	-	$0.00	$0.00

Showing 81-100 of 635 models