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)
QwQ 32B-Preview Alibaba	15.2	64.8%	-	55.7%	0.28	45	$0.12	$0.18
GLM-4.5V (Reasoning) Z AI	15.1	78.8%	-	68.4%	1.04	54	$0.60	$1.80
Mistral Large 2 (Nov '24) Mistral	15.1	69.7%	-	48.6%	0.50	37	$2.00	$6.00
Mistral Small 3.2 Mistral	15.1	68.1%	-	50.5%	0.35	131	$0.10	$0.30
Baidu: ERNIE 4.5 300B A47B Baidu	15.0	77.6%	123K	81.1%	1.67	26	$0.28	$1.10
NVIDIA: Llama 3.1 Nemotron Ultra 253B v1 NVIDIA	15.0	82.5%	131K	72.8%	0.67	42	$0.60	$1.80
Qwen3 30B A3B 2507 Instruct Alibaba	15.0	77.7%	-	65.9%	0.93	91	$0.20	$0.80
NVIDIA Nemotron Nano 12B v2 VL (Reasoning) NVIDIA	14.9	75.9%	-	57.2%	0.21	137	$0.20	$0.60
Solar Pro 2 (Reasoning) Upstage	14.9	80.5%	-	68.7%	-	-	$0.00	$0.00
Gemma 4 E4B (Non-reasoning)New Google	14.8	-	-	54.9%	-	-	$0.00	$0.00
Ministral 3 8B Mistral	14.8	64.2%	-	47.1%	0.29	197	$0.15	$0.15
NVIDIA Nemotron Nano 9B V2 (Reasoning) NVIDIA	14.8	74.2%	-	57.0%	0.22	159	$0.04	$0.16
Gemini 2.0 Flash-Lite (Feb '25) Google	14.7	72.4%	-	53.5%	-	-	$0.00	$0.00
NVIDIA Nemotron 3 Nano 4BNew NVIDIA	14.7	-	-	51.3%	-	-	$0.00	$0.00
Qwen3.5 2B (Non-reasoning)New Alibaba	14.7	-	-	43.8%	0.21	272	$0.02	$0.10
Llama Nemotron Super 49B v1.5 (Non-reasoning) NVIDIA	14.6	69.2%	-	48.1%	0.38	60	$0.10	$0.40
Google: Gemini 2.0 Flash Lite Google	14.5	-	1049K	54.2%	-	-	$0.00	$0.00
Llama 3.3 Instruct 70B Meta	14.5	71.3%	-	49.8%	0.51	98	$0.58	$0.71
Mistral Small 3.1 Mistral	14.5	65.9%	-	45.4%	0.56	151	$0.10	$0.30
OpenAI: GPT-4o (2024-05-13) OpenAI	14.5	74.0%	128K	52.6%	0.56	95	$5.00	$15.00

Showing 281-300 of 645 models