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)
LiquidAI: LFM2-24B-A2BNew Liquid AI	10.5	-	33K	47.4%	0.32	97	$0.03	$0.12
Qwen3.5 0.8B (Reasoning)New Alibaba	10.5	-	-	11.1%	-	-	$0.01	$0.05
Microsoft: Phi 4 Microsoft	10.4	71.4%	16K	57.5%	0.50	38	$0.13	$0.50
Claude 3 Sonnet Anthropic	10.3	57.9%	-	40.0%	-	-	$3.00	$15.00
Gemma 3 27B Instruct Google	10.3	66.9%	-	42.8%	0.79	26	$0.00	$0.00
Nova Micro Amazon	10.3	53.1%	-	35.8%	0.60	352	$0.04	$0.14
Mistral Small (Sep '24) Mistral	10.2	52.9%	-	38.1%	0.55	155	$0.20	$0.60
Gemini 1.0 Ultra Google	10.1	-	-	-	-	-	$0.00	$0.00
Gemma 3n E4B Instruct Preview (May '25) Google	10.1	48.3%	-	27.8%	-	-	$0.00	$0.00
NVIDIA: Nemotron Nano 12B 2 VL NVIDIA	10.1	64.9%	131K	43.9%	0.59	157	$0.20	$0.60
Phi-3 Mini Instruct 3.8B Microsoft	10.1	43.5%	-	31.9%	-	-	$0.00	$0.00
Phi-4 Multimodal Instruct Microsoft	10.0	48.5%	-	31.5%	0.36	17	$0.00	$0.00
Qwen2.5 Coder Instruct 7B Alibaba	10.0	47.3%	-	33.9%	-	-	$0.00	$0.00
Mistral Large Mistral	9.9	51.5%	128K	35.1%	-	-	$4.00	$12.00
Qwen3.5 0.8B (Non-reasoning)New Alibaba	9.9	-	-	23.6%	0.44	267	$0.01	$0.05
Mistral: Mixtral 8x22B Instruct Mistral	9.8	53.7%	66K	33.2%	-	-	$0.00	$0.00
Llama 2 Chat 7B Meta	9.7	16.4%	-	22.7%	1.03	122	$0.05	$0.25
Llama 3.2 Instruct 3B Meta	9.7	34.7%	-	25.5%	0.66	52	$0.15	$0.15
Jamba Reasoning 3B AI21 Labs	9.6	57.7%	-	33.3%	-	-	$0.00	$0.00
Qwen3 VL 4B Instruct Alibaba	9.6	63.4%	-	37.1%	-	-	$0.00	$0.00

Showing 401-420 of 667 models