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)
Nova Pro Amazon	13.5	69.1%	-	49.9%	-	-	$0.80	$3.20
Llama 3.1 Nemotron Instruct 70B Meta	13.4	69.0%	-	46.5%	0.56	36	$1.20	$1.20
Grok Beta xAI	13.3	70.3%	-	47.1%	-	-	$0.00	$0.00
Qwen2.5 Instruct 32B Alibaba	13.2	69.7%	-	46.6%	-	-	$0.00	$0.00
Qwen3 8B (Reasoning) Alibaba	13.2	74.3%	-	58.9%	0.93	91	$0.18	$2.10
Mistral Large 2407 mistralai	13.0	68.3%	131K	47.2%	-	-	$2.00	$6.00
OpenAI: GPT-4.1 Nano openai	13.0	65.7%	1048K	51.2%	0.39	143	$0.10	$0.40
Qwen2.5 Coder 32B Instruct qwen	12.9	63.5%	33K	41.7%	-	-	$0.20	$0.20
Qwen3 4B 2507 Instruct Alibaba	12.9	67.2%	-	51.7%	-	-	$0.00	$0.00
OpenAI: GPT-4 openai	12.8	-	8K	-	0.96	44	$30.00	$60.00
Qwen: Qwen3 14B qwen	12.8	67.5%	41K	47.0%	0.96	65	$0.35	$1.40
Nova Lite Amazon	12.7	59.0%	-	43.3%	0.39	214	$0.06	$0.24
Gemini 2.5 Flash-Lite (Non-reasoning) Google	12.7	72.4%	-	47.4%	0.40	196	$0.10	$0.40
Z.ai: GLM 4.5V z-ai	12.7	75.1%	66K	57.3%	28.79	47	$0.60	$1.80
Mistral: Mistral Small 3 mistralai	12.7	65.2%	33K	46.2%	0.29	187	$0.10	$0.30
OpenAI: GPT-4o-mini openai	12.6	64.8%	128K	42.6%	0.49	54	$0.15	$0.60
Hermes 4 - Llama-3.1 70B (Non-reasoning) Meta	12.6	66.4%	-	49.1%	0.56	87	$0.13	$0.40
DeepSeek-V2.5 (Dec '24) DeepSeek	12.5	-	-	-	-	-	$0.00	$0.00
Qwen3 30B A3B (Non-reasoning) Alibaba	12.5	71.0%	-	51.5%	1.02	63	$0.20	$0.80
Qwen3 4B (Non-reasoning) Alibaba	12.5	58.6%	-	39.8%	0.94	105	$0.11	$0.42

Showing 281-300 of 604 models