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 1.7B (Reasoning) Alibaba	8.0	57.0%	-	35.6%	0.95	138	$0.11	$1.26
Jamba 1.6 Mini AI21 Labs	7.9	36.7%	-	30.0%	0.76	186	$0.20	$0.40
Apertus 70B Instruct Swiss AI Initiative	7.7	-	-	27.2%	-	-	$0.82	$2.92
Gemma 3 270M Google	7.7	5.5%	-	22.4%	-	-	$0.00	$0.00
IBM: Granite 4.0 Micro IBM	7.7	44.7%	131K	33.6%	-	-	$0.00	$0.00
Mistral: Mixtral 8x7B Instruct Mistral	7.7	38.7%	33K	29.2%	-	-	$0.49	$0.62
DeepHermes 3 - Llama-3.1 8B Preview (Non-reasoning) Nous Research	7.6	36.5%	-	27.0%	-	-	$0.00	$0.00
Claude Instant Anthropic	7.4	43.4%	-	33.0%	-	-	$0.00	$0.00
Command-R (Mar '24) Cohere	7.4	33.8%	-	28.4%	-	-	$0.50	$1.50
Llama 65B Meta	7.4	-	-	-	-	-	$0.00	$0.00
Mistral 7B Instruct Mistral	7.4	24.5%	-	17.7%	0.31	183	$0.25	$0.25
Qwen Chat 14B Alibaba	7.4	-	-	-	-	-	$0.00	$0.00
Granite 4.0 1B IBM	7.3	32.5%	-	28.1%	-	-	$0.00	$0.00
Molmo2-8B Allen Institute for AI	7.3	-	-	42.5%	-	-	$0.00	$0.00
Granite 3.3 8B (Non-reasoning) IBM	7.0	46.8%	-	33.8%	20.73	377	$0.03	$0.25
LFM2 8B A1B Liquid AI	7.0	50.5%	-	34.4%	-	-	$0.00	$0.00
Qwen3 1.7B (Non-reasoning) Alibaba	6.8	41.1%	-	28.3%	0.93	141	$0.11	$0.42
Qwen3 0.6B (Reasoning) Alibaba	6.5	34.7%	-	23.9%	0.89	191	$0.11	$1.26
Gemma 3n E4B Instruct Google	6.4	48.8%	-	29.6%	0.36	16	$0.02	$0.04
Llama 3 Instruct 8B Meta	6.4	40.5%	-	29.6%	0.50	83	$0.04	$0.14

Showing 441-460 of 644 models