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)
Nova 2.0 Lite (medium) Amazon	29.7	81.3%	-	76.8%	12.58	191	$0.30	$2.50
Gemini 2.5 Pro Preview (May' 25) Google	29.5	83.7%	-	82.2%	-	-	$1.25	$10.00
Qwen3 235B A22B 2507 (Reasoning) Alibaba	29.5	84.3%	-	79.0%	1.32	51	$0.70	$8.40
DeepSeek: DeepSeek V3.2 Speciale DeepSeek	29.4	86.3%	164K	87.1%	-	-	$0.00	$0.00
ERNIE 5.0 Thinking Preview Baidu	29.1	83.0%	-	77.7%	-	-	$0.00	$0.00
Grok 4.20 0309 v2 (Non-reasoning)New xAI	29.0	-	-	77.6%	0.45	85	$2.00	$6.00
xAI: Grok Code Fast 1 xAI	28.7	79.3%	256K	72.7%	3.73	151	$0.20	$1.50
DeepSeek V3.1 Terminus (Non-reasoning) DeepSeek	28.5	83.6%	-	75.1%	-	-	$0.27	$1.00
DeepSeek: DeepSeek V3.2 Exp DeepSeek	28.4	83.6%	164K	73.8%	0.77	80	$0.28	$0.42
Nemotron Cascade 2 30B A3BNew NVIDIA	28.4	-	-	75.8%	-	-	$0.00	$0.00
Apriel-v1.5-15B-Thinker ServiceNow	28.3	77.3%	-	71.3%	-	-	$0.00	$0.00
Qwen: Qwen3 Coder NextNew Alibaba	28.3	-	262K	73.7%	0.77	156	$0.35	$1.20
DeepSeek: DeepSeek V3.1 DeepSeek	28.1	83.3%	33K	73.5%	-	-	$0.56	$1.67
Nova 2.0 Omni (medium) Amazon	28.0	80.9%	-	76.0%	-	-	$0.30	$2.50
Mistral: Mistral Small 4New Mistral	27.8	-	262K	76.9%	0.55	172	$0.15	$0.60
DeepSeek V3.1 (Reasoning) DeepSeek	27.7	85.1%	-	77.9%	-	-	$0.59	$1.69
Apriel-v1.6-15B-Thinker ServiceNow	27.6	79.0%	-	73.3%	-	-	$0.00	$0.00
Qwen3 VL 235B A22B (Reasoning) Alibaba	27.6	83.6%	-	77.2%	1.26	44	$0.70	$8.40
OpenAI: GPT-5.1 OpenAI	27.4	80.1%	400K	64.3%	0.73	120	$1.25	$10.00
Qwen: Qwen3.5-9BNew Alibaba	27.3	-	262K	78.6%	-	-	$0.00	$0.00

Showing 141-160 of 667 models