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)
Devstral Small (Jul '25) Mistral Intelligence: 9.1Input (1M): $0.00	9.1	62.2%	-	41.4%	-	-	$0.00	$0.00
Perplexity: Sonar Pro Perplexity Intelligence: 9.1Input (1M): $0.00	9.1	75.5%	200K	57.8%	-	-	$0.00	$0.00
QwQ 32B-Preview Alibaba Intelligence: 9.1Input (1M): $0.00	9.1	64.8%	-	55.7%	-	-	$0.00	$0.00
GLM-4.5V (Reasoning) Z AI Intelligence: 9.0Input (1M): $0.60	9.0	78.8%	-	68.4%	-	-	$0.60	$1.80
Ministral 3 8B Mistral Intelligence: 9.0Input (1M): $0.15	9.0	64.2%	-	47.1%	0.56	110	$0.15	$0.15
Mistral Large 2 (Nov '24) Mistral Intelligence: 9.0Input (1M): $0.00	9.0	69.7%	-	48.6%	-	-	$0.00	$0.00
ERNIE 4.5 300B A47B Baidu Intelligence: 8.9Input (1M): $0.28	8.9	77.6%	-	81.1%	-	-	$0.28	$1.10
Llama 3.1 Nemotron Ultra 253B v1 (Reasoning) NVIDIA Intelligence: 8.9Input (1M): $0.60	8.9	82.5%	-	72.8%	0.69	53	$0.60	$1.80
Qwen3 30B A3B 2507 Instruct Alibaba Intelligence: 8.9Input (1M): $0.20	8.9	77.7%	-	65.9%	-	-	$0.20	$0.80
Hermes 4 - Llama-3.1 405B (Reasoning) Nous Research Intelligence: 8.8Input (1M): $1.00	8.8	82.9%	-	72.7%	0.75	43	$1.00	$3.00
NVIDIA Nemotron Nano 12B v2 VL (Reasoning) NVIDIA Intelligence: 8.8Input (1M): $0.20	8.8	75.9%	-	57.2%	15.65	22	$0.20	$0.60
Solar Pro 2 (Reasoning) Upstage Intelligence: 8.8Input (1M): $0.00	8.8	80.5%	-	68.7%	-	-	$0.00	$0.00
Gemma 4 E4B (Non-reasoning)New Google Intelligence: 8.7Input (1M): $0.02	8.7	-	-	54.9%	0.28	44	$0.02	$0.10
Granite 4.1 30BNew IBM Intelligence: 8.7Input (1M): $0.00	8.7	-	-	48.1%	-	-	$0.00	$0.00
NVIDIA Nemotron Nano 9B V2 (Reasoning) NVIDIA Intelligence: 8.7Input (1M): $0.04	8.7	74.2%	-	57.0%	6.05	95	$0.04	$0.16
Gemini 2.0 Flash-Lite (Feb '25) Google Intelligence: 8.6Input (1M): $0.00	8.6	72.4%	-	53.5%	-	-	$0.00	$0.00
Hermes 4 - Llama-3.1 405B (Non-reasoning) Nous Research Intelligence: 8.6Input (1M): $1.00	8.6	72.9%	-	53.6%	0.75	43	$1.00	$3.00
NVIDIA Nemotron 3 Nano 4BNew NVIDIA Intelligence: 8.6Input (1M): $0.00	8.6	-	-	51.3%	-	-	$0.00	$0.00
Llama Nemotron Super 49B v1.5 (Non-reasoning) NVIDIA Intelligence: 8.5Input (1M): $0.40	8.5	69.2%	-	48.1%	13.59	24	$0.40	$0.40
Qwen: Qwen3 32B Alibaba Intelligence: 8.5Input (1M): $0.16	8.5	72.7%	131K	53.5%	-	-	$0.16	$0.64

Showing 441-460 of 793 models