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)
Auto Router openrouter	-	-	2000K	-	-	-	$-1000000.00	$-1000000.00
Claude 4.1 Opus (Reasoning)New Anthropic	31.9	88.0%	200K	80.9%	1.29	47	$15.00	$75.00
AllenAI: Olmo 3.1 32B Instruct allenai	-	-	66K	-	0.24	44	$0.20	$0.60
AllenAI: Olmo 3.1 32B Think allenai	-	-	66K	-	0.54	76	$0.15	$0.50
Kwaipilot: KAT-Coder-Pro V1 kwaipilot	-	-	256K	-	1.98	56	$0.21	$0.83
Mistral: Mistral Medium 3.1 mistralai	-	-	131K	-	0.41	93	$0.40	$2.00
Qwen: Qwen Plus 0728 (thinking) qwen	-	-	1000K	-	-	-	$0.40	$1.20
Magistral Small 1New Mistral	16.8	74.6%	262K	64.1%	-	-	$0.00	$0.00
Gemma 3n E4B Instruct Preview (May '25)New Google	10.1	48.3%	33K	27.8%	-	-	$0.00	$0.00
Gemma 3 27B InstructNew Google	10.2	66.9%	131K	42.8%	0.85	34	$0.00	$0.00
DeepHermes 3 - Mistral 24B Preview (Non-reasoning) Nous Research	10.9	58.0%	131K	38.2%	-	-	$0.00	$0.00
Falcon-H1R-7B TII UAE	15.8	72.5%	131K	66.1%	-	-	$0.00	$0.00
K-EXAONE (Reasoning) LG AI Research	32.1	83.8%	33K	78.3%	-	-	$0.00	$0.00
K-EXAONE (Non-reasoning) LG AI Research	23.0	81.0%	33K	69.5%	-	-	$0.00	$0.00
K2-V2 (low) MBZUAI Institute of Foundation Models	14.4	71.3%	131K	54.1%	-	-	$0.00	$0.00
K2-V2 (high) MBZUAI Institute of Foundation Models	20.7	78.6%	131K	68.1%	-	-	$0.00	$0.00
K2 Think V2 MBZUAI Institute of Foundation Models	24.5	-	131K	71.3%	-	-	$0.00	$0.00
Mi:dm K 2.5 Pro Korea Telecom	23.0	80.9%	33K	70.1%	-	-	$0.00	$0.00
GPT-4o mini Realtime (Dec '24) OpenAI	-	-	128K	-	-	-	$0.00	$0.00
GPT-4o (March 2025, chatgpt-4o-latest) OpenAI	18.6	80.3%	128K	65.5%	-	-	$0.00	$0.00

Showing 201-220 of 635 models