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)
Kimi Linear 48B A3B Instruct MoonshotAI	14.4	58.5%	-	41.2%	-	-	$0.00	$0.00
Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning) Meta	14.4	55.6%	-	40.8%	-	-	$0.00	$0.00
K2-V2 (low) Unknown	14.4	71.3%	-	54.1%	-	-	$0.00	$0.00
Qwen: Qwen3 VL 8B Instruct qwen	14.3	68.6%	131K	42.7%	1.03	139	$0.18	$0.70
Llama 3.3 Nemotron Super 49B v1 (Non-reasoning) Meta	14.3	69.8%	-	51.7%	-	-	$0.00	$0.00
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%	0.94	104	$0.11	$1.26
OpenAI: GPT-4o openai	14.1	77.3%	128K	51.1%	-	-	$0.00	$0.00
Llama 3.1 Tulu3 405B Meta	14.1	71.6%	-	51.6%	-	-	$0.00	$0.00
Mistral: Pixtral Large 2411 mistralai	14.0	70.1%	131K	50.5%	0.42	56	$2.00	$6.00
Ring-flash-2.0 Unknown	14.0	79.3%	-	72.5%	1.42	83	$0.14	$0.57
AllenAI: Olmo 3.1 32B Think allenai	13.9	76.3%	66K	59.1%	0.46	90	$0.00	$0.00
Grok 2 (Dec '24) xAI	13.9	70.9%	-	51.0%	-	-	$0.00	$0.00
GPT-5 nano (minimal) OpenAI	13.8	55.6%	-	42.8%	0.67	128	$0.05	$0.40
Gemini 1.5 Flash (Sep '24) Google	13.8	68.0%	-	46.3%	-	-	$0.00	$0.00
OpenAI: GPT-4 Turbo openai	13.7	69.4%	128K	-	1.12	37	$10.00	$30.00
Qwen3 VL 4B (Reasoning) Alibaba	13.7	70.0%	-	49.4%	-	-	$0.00	$0.00
Solar Pro 2 (Non-reasoning) Unknown	13.6	75.0%	-	56.1%	-	-	$0.00	$0.00
Meta: Llama 4 Scout meta-llama	13.5	75.2%	328K	58.7%	0.45	130	$0.17	$0.66
Cohere: Command A cohere	13.5	71.2%	256K	52.7%	0.36	47	$2.50	$10.00

Showing 261-280 of 604 models