AI Models Leaderboard 2026

Compare the best AI models, LLM APIs, pricing, context windows, and performance benchmarks updated dynamically.

Model	Intelligence	MMLU Pro	Context	GPQA	TTFT (s)	Speed (T/s)	Input Price (1M)	Output Price (1M)
GLM-4.7 (Non-reasoning) Zhipu	34.2	79.4%	-	66.4%	0.72	103	$0.55	$2.15
DeepSeek: DeepSeek V3.2 Speciale deepseek	34.1	86.3%	164K	87.1%	-	-	$0.00	$0.00
DeepSeek V3.1 Terminus (Reasoning) DeepSeek	33.9	85.1%	-	79.2%	-	-	$0.40	$2.00
OpenAI: GPT-5.2 openai	33.6	81.4%	400K	71.2%	0.60	62	$1.75	$14.00
Google: Gemini 3.1 Flash Lite PreviewNew google	33.5	-	1049K	82.2%	5.07	292	$0.25	$1.50
Doubao Seed Code Unknown	33.5	85.4%	-	76.4%	-	-	$0.00	$0.00
OpenAI: gpt-oss-120b openai	33.3	80.8%	131K	78.2%	0.52	271	$0.15	$0.60
OpenAI: o4 Mini High openai	33.1	83.2%	200K	78.4%	18.77	136	$1.10	$4.40
OpenAI: o4 Mini openai	33.1	83.2%	200K	78.4%	18.77	136	$1.10	$4.40
Claude 4 Sonnet (Non-reasoning) Anthropic	33.0	83.7%	-	68.3%	1.11	50	$3.00	$15.00
DeepSeek: DeepSeek V3.2 Exp deepseek	32.9	85.0%	164K	79.7%	1.24	29	$0.28	$0.42
Inception: Mercury 2New inception	32.8	-	128K	77.0%	3.81	795	$0.25	$0.75
GLM-4.6 (Reasoning) Zhipu	32.5	82.9%	-	78.0%	0.68	87	$0.57	$2.20
Qwen3 Max Thinking (Preview) Alibaba	32.5	82.4%	-	77.6%	1.72	42	$1.20	$6.00
Qwen3.5 9B (Reasoning)New Alibaba	32.4	-	-	80.6%	4.02	133	$0.10	$0.15
DeepSeek: DeepSeek V3.2 deepseek	32.1	83.7%	164K	75.1%	1.40	29	$0.28	$0.42
Grok 3 mini Reasoning (high) xAI	32.1	82.8%	-	79.1%	0.45	198	$0.30	$0.50
K-EXAONE (Reasoning) LG	32.1	83.8%	-	78.3%	-	-	$0.00	$0.00
Nova 2.0 Pro Preview (low) Amazon	31.9	82.2%	-	75.1%	3.50	177	$1.25	$10.00
Claude 4.1 Opus (Reasoning) Anthropic	31.9	88.0%	-	80.9%	8.27	41	$15.00	$75.00

Showing 61-80 of 604 models