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)
EXAONE 4.0 32B (Non-reasoning) LG AI Research	11.7	76.8%	-	62.8%	-	-	$0.00	$0.00
Grok-1 xAI	11.7	-	-	-	-	-	$0.00	$0.00
Qwen2 Instruct 72B Alibaba	11.7	62.2%	-	37.1%	-	-	$0.00	$0.00
Ministral 3 3B Mistral	11.2	52.4%	-	35.8%	0.29	291	$0.10	$0.10
Gemini 1.5 Flash-8B Google	11.1	56.9%	-	35.9%	-	-	$0.00	$0.00
DeepHermes 3 - Mistral 24B Preview (Non-reasoning) Nous Research	10.9	58.0%	-	38.2%	-	-	$0.00	$0.00
Jamba 1.7 Large AI21 Labs	10.9	57.7%	-	39.0%	0.88	54	$2.00	$8.00
Granite 4.0 H Small IBM	10.8	62.4%	-	41.6%	8.69	435	$0.06	$0.25
Jamba 1.5 Large AI21 Labs	10.7	57.2%	-	42.7%	-	-	$2.00	$8.00
Qwen3 Omni 30B A3B Instruct Alibaba	10.7	72.5%	-	62.0%	0.87	108	$0.25	$0.97
DeepSeek-Coder-V2 DeepSeek	10.6	-	-	-	-	-	$0.00	$0.00
Jamba 1.6 Large AI21 Labs	10.6	56.5%	-	38.7%	0.76	54	$2.00	$8.00
Nous: Hermes 3 70B Instruct Nous Research	10.6	57.1%	131K	40.1%	0.43	26	$0.30	$0.30
OLMo 2 32B Allen Institute for AI	10.6	51.1%	-	32.8%	-	-	$0.00	$0.00
Qwen: Qwen3 8B Alibaba	10.6	64.3%	41K	45.2%	0.90	87	$0.18	$0.70
Gemini 1.5 Flash (May '24) Google	10.5	57.4%	-	32.4%	-	-	$0.00	$0.00
LiquidAI: LFM2-24B-A2BNew Liquid AI	10.5	-	33K	47.4%	0.26	60	$0.03	$0.12
Qwen3.5 0.8B (Reasoning)New Alibaba	10.5	-	-	11.1%	-	-	$0.01	$0.05
Microsoft: Phi 4 Microsoft Azure	10.4	71.4%	16K	57.5%	0.49	37	$0.13	$0.50
Claude 3 Sonnet Anthropic	10.3	57.9%	-	40.0%	-	-	$3.00	$15.00

Showing 361-380 of 645 models