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)
Gemini 2.5 Flash (Non-reasoning) Google	20.6	80.9%	-	68.3%	0.40	206	$0.30	$2.50
K2-V2 (high) MBZUAI Institute of Foundation Models	20.6	78.6%	-	68.1%	-	-	$0.00	$0.00
o1-mini OpenAI	20.4	74.2%	-	60.3%	-	-	$0.00	$0.00
Qwen: Qwen3 Next 80B A3B Instruct Alibaba	20.1	81.9%	262K	73.8%	1.05	173	$0.50	$2.00
GPT-4.5 (Preview) OpenAI	20.0	-	-	-	-	-	$0.00	$0.00
Qwen: Qwen3 Coder 30B A3B Instruct Alibaba	20.0	70.6%	160K	51.6%	1.49	28	$0.45	$2.25
Tri-21B-think PreviewNew Trillion Labs	20.0	-	-	53.8%	-	-	$0.00	$0.00
Qwen: Qwen3 235B A22B Alibaba	19.8	82.8%	131K	70.0%	1.20	63	$0.70	$8.40
Qwen: QwQ 32B Alibaba	19.7	76.4%	131K	59.3%	0.43	32	$0.66	$1.00
Qwen3 VL 30B A3B (Reasoning) Alibaba	19.7	80.7%	-	72.0%	1.01	129	$0.20	$2.40
Gemini 2.0 Flash Thinking Experimental (Jan '25) Google	19.6	79.8%	-	70.1%	-	-	$0.00	$0.00
Devstral Small 2 Mistral	19.5	67.8%	-	53.2%	0.41	77	$0.00	$0.00
Google: Gemini 2.5 Flash Lite Preview 09-2025 Google	19.4	79.6%	1049K	65.1%	-	-	$0.10	$0.40
Motif-2-12.7B-Reasoning Motif Technologies	19.1	79.6%	-	69.5%	-	-	$0.00	$0.00
Ling-1T InclusionAI	19.0	82.2%	-	71.9%	-	-	$0.00	$0.00
Nova Premier Amazon	19.0	73.3%	-	56.9%	0.91	63	$2.50	$12.50
DeepSeek R1 (Jan '25) DeepSeek	18.8	84.4%	-	70.8%	-	-	$1.35	$4.00
Gemma 4 E4B (Reasoning)New Google	18.8	-	-	57.6%	-	-	$0.00	$0.00
Magistral Medium 1 Mistral	18.8	75.3%	-	67.9%	-	-	$0.00	$0.00
Mistral: Mistral Medium 3 Mistral	18.8	76.0%	131K	57.8%	0.44	53	$0.40	$2.00

Showing 201-220 of 645 models