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 (low) Amazon	24.6	78.8%	-	69.8%	4.71	205	$0.30	$2.50
Perplexity: Sonar Reasoning Pro Perplexity	24.6	-	128K	-	-	-	$0.00	$0.00
gpt-oss-20B (high) OpenAI	24.5	74.8%	-	68.8%	0.37	254	$0.06	$0.20
OpenAI: gpt-oss-120b OpenAI	24.5	77.5%	131K	67.2%	0.50	195	$0.15	$0.60
GPT-5.4 nano (Non-Reasoning)New OpenAI	24.4	-	-	55.8%	0.44	189	$0.20	$1.25
MiniMax M1 80k MiniMax	24.4	81.6%	-	69.7%	-	-	$0.55	$2.20
Gemini 2.5 Flash Preview (Reasoning) Google	24.3	80.0%	-	69.8%	-	-	$0.00	$0.00
NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) NVIDIA	24.3	79.4%	-	75.7%	2.74	115	$0.06	$0.24
K2 Think V2 MBZUAI Institute of Foundation Models	24.1	-	-	71.3%	-	-	$0.00	$0.00
GPT-5 (minimal) OpenAI	23.9	80.6%	-	67.3%	1.11	70	$1.25	$10.00
LongCat Flash LiteNew LongCat	23.9	-	-	63.6%	3.19	118	$0.00	$0.00
HyperCLOVA X SEED Think (32B) Naver	23.7	78.5%	-	61.5%	-	-	$0.00	$0.00
o1-preview OpenAI	23.7	-	-	-	-	-	$16.50	$66.00
Grok 4.1 Fast (Non-reasoning) xAI	23.6	74.3%	-	63.7%	0.30	115	$0.20	$0.50
K-EXAONE (Non-reasoning) LG AI Research	23.4	81.0%	-	69.5%	-	-	$0.00	$0.00
Z.ai: GLM 4.6V Z AI	23.4	79.9%	131K	71.9%	1.21	28	$0.30	$0.90
GPT-5.4 mini (Non-Reasoning)New OpenAI	23.3	-	-	60.6%	0.47	150	$0.75	$4.50
Nova 2.0 Omni (low) Amazon	23.2	79.8%	-	69.9%	-	-	$0.30	$2.50
Z.ai: GLM 4.5 Air Z AI	23.2	81.5%	131K	73.3%	0.61	80	$0.20	$1.10
Grok 4 Fast (Non-reasoning) xAI	23.1	73.0%	-	60.6%	0.28	173	$0.20	$0.50

Showing 161-180 of 645 models