AI Models Leaderboard 2026

Compare the latest published AI model snapshot across pricing, context windows, latency, and benchmark performance.

Model	Intelligence	MMLU Pro	Context	GPQA	TTFT (s)	Speed (T/s)	Input Price (1M)	Output Price (1M)
Qwen3 32B (Non-reasoning) Alibaba	14.5	72.7%	-	53.5%	0.97	106	$0.70	$2.80
K2-V2 (low) MBZUAI Institute of Foundation Models	14.4	71.3%	-	54.1%	-	-	$0.00	$0.00
Kimi Linear 48B A3B Instruct Kimi	14.4	58.5%	-	41.2%	-	-	$0.00	$0.00
Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning) NVIDIA	14.4	55.6%	-	40.8%	-	-	$0.00	$0.00
Llama 3.3 Nemotron Super 49B v1 (Non-reasoning) NVIDIA	14.3	69.8%	-	51.7%	-	-	$0.00	$0.00
Qwen: Qwen3 VL 8B Instruct Alibaba	14.3	68.6%	131K	42.7%	0.95	142	$0.18	$0.70
Claude 3.5 Sonnet (June '24) Anthropic	14.2	75.1%	-	56.0%	-	-	$3.00	$15.00
Qwen3 4B (Reasoning) Alibaba	14.2	69.6%	-	52.2%	0.96	103	$0.11	$1.26
Llama 3.1 Tulu3 405B Allen Institute for AI	14.1	71.6%	-	51.6%	-	-	$0.00	$0.00
OpenAI: GPT-4o OpenAI	14.1	77.3%	128K	51.1%	-	-	$0.00	$0.00
Mistral: Pixtral Large 2411 Mistral	14.0	70.1%	131K	50.5%	0.45	54	$2.00	$6.00
Ring-flash-2.0 InclusionAI	14.0	79.3%	-	72.5%	1.65	88	$0.14	$0.57
Grok 2 (Dec '24) xAI	13.9	70.9%	-	51.0%	-	-	$0.00	$0.00
Olmo 3.1 32B Think Allen Institute for AI	13.9	76.3%	-	59.1%	0.40	99	$0.00	$0.00
Gemini 1.5 Flash (Sep '24) Google	13.8	68.0%	-	46.3%	-	-	$0.00	$0.00
GPT-5 nano (minimal) OpenAI	13.8	55.6%	-	42.8%	0.85	122	$0.05	$0.40
OpenAI: GPT-4 Turbo OpenAI	13.7	69.4%	128K	-	1.26	27	$10.00	$30.00
Qwen3 VL 4B (Reasoning) Alibaba	13.7	70.0%	-	49.4%	-	-	$0.00	$0.00
Solar Pro 2 (Non-reasoning) Upstage	13.6	75.0%	-	56.1%	-	-	$0.00	$0.00
Cohere: Command A Cohere	13.5	71.2%	256K	52.7%	0.56	36	$2.50	$10.00

Showing 301-320 of 645 models