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)
DeepSeek-V2.5 (Dec '24) DeepSeek	12.5	-	-	-	-	-	$0.00	$0.00
Llama 3.1 Instruct 70B Meta	12.5	67.6%	-	40.9%	0.43	31	$0.56	$0.56
Qwen3 30B A3B (Non-reasoning) Alibaba	12.5	71.0%	-	51.5%	1.03	69	$0.20	$0.80
Qwen3 4B (Non-reasoning) Alibaba	12.5	58.6%	-	39.8%	0.94	104	$0.11	$0.42
Anthropic: Claude 3 Haiku Anthropic	12.3	-	200K	37.4%	0.48	133	$0.25	$1.25
DeepSeek-V2.5 DeepSeek	12.3	-	-	-	-	-	$0.00	$0.00
Gemini 2.0 Flash Thinking Experimental (Dec '24) Google	12.3	-	-	-	-	-	$0.00	$0.00
Sarvam 30B (high)New Sarvam	12.3	-	-	63.3%	1.19	137	$0.00	$0.00
AllenAI: Olmo 3.1 32B InstructNew Allen Institute for AI	12.2	-	66K	53.9%	0.24	54	$0.20	$0.60
AllenAI: Olmo 3 32B Think Allen Institute for AI	12.1	75.9%	66K	61.0%	-	-	$0.00	$0.00
DeepSeek R1 Distill Llama 8B DeepSeek	12.1	54.3%	-	30.2%	-	-	$0.00	$0.00
Gemma 4 E2B (Non-reasoning)New Google	12.1	-	-	40.5%	-	-	$0.00	$0.00
Mistral: Saba Mistral	12.1	61.1%	33K	42.4%	-	-	$0.00	$0.00
Gemini 1.5 Pro (May '24) Google	12.0	65.7%	-	37.1%	-	-	$0.00	$0.00
Qwen: Qwen-Turbo Alibaba	12.0	63.3%	131K	41.0%	1.01	70	$0.05	$0.20
R1 1776 Perplexity	12.0	-	-	-	-	-	$0.00	$0.00
Reka Flash (Sep '24) Reka AI	12.0	-	-	-	1.26	85	$0.20	$0.80
Llama 3.2 Instruct 90B (Vision) Meta	11.9	67.1%	-	43.2%	0.40	42	$0.72	$0.72
Solar Mini Upstage	11.9	-	-	-	1.38	93	$0.15	$0.15
Llama 3.1 Instruct 8B Meta	11.8	47.6%	-	25.9%	0.38	177	$0.10	$0.10

Showing 341-360 of 645 models