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)
Sarvam 105B (high)New Sarvam	18.2	-	-	73.8%	1.25	153	$0.00	$0.00
Gemini 2.0 Pro Experimental (Feb '25) Google	18.1	80.5%	-	62.2%	-	-	$0.00	$0.00
Claude 3 Opus Anthropic	18.0	69.6%	-	48.9%	-	-	$15.00	$75.00
Devstral Small (May '25) Mistral	18.0	63.2%	-	43.4%	-	-	$0.00	$0.00
Nova 2.0 Lite (Non-reasoning) Amazon	18.0	74.3%	-	60.3%	0.81	222	$0.30	$2.50
Sonar Reasoning Perplexity	17.9	-	-	62.3%	-	-	$0.00	$0.00
Gemini 2.5 Flash Preview (Non-reasoning) Google	17.8	78.3%	-	59.4%	-	-	$0.00	$0.00
Gemini 2.5 Flash-Lite (Reasoning) Google	17.6	75.9%	-	62.5%	15.95	292	$0.10	$0.40
Hermes 4 - Llama-3.1 405B (Non-reasoning) Nous Research	17.6	72.9%	-	53.6%	0.74	34	$1.00	$3.00
Llama 3.1 Instruct 405B Meta	17.4	73.2%	-	51.5%	0.73	32	$2.75	$6.50
GPT-4o (Nov '24) OpenAI	17.3	74.8%	-	54.3%	0.48	155	$2.50	$10.00
DeepSeek: R1 Distill Qwen 32B DeepSeek	17.2	73.9%	33K	61.5%	-	-	$0.00	$0.00
Qwen: Qwen3 VL 32B Instruct Alibaba	17.2	79.1%	131K	67.1%	1.26	81	$0.70	$2.80
Z.ai: GLM 4.6V Z AI	17.1	75.2%	131K	56.6%	4.86	30	$0.30	$0.90
Qwen3 235B A22B (Non-reasoning) Alibaba	17.0	76.2%	-	61.3%	1.20	64	$0.70	$2.80
Gemini 2.0 Flash (experimental) Google	16.8	78.2%	-	63.6%	-	-	$0.00	$0.00
Magistral Small 1 Mistral	16.8	74.6%	-	64.1%	-	-	$0.00	$0.00
EXAONE 4.0 32B (Reasoning) LG AI Research	16.7	81.8%	-	73.9%	-	-	$0.00	$0.00
Qwen3 VL 8B (Reasoning) Alibaba	16.7	74.9%	-	57.9%	1.25	134	$0.18	$2.10
Nova 2.0 Omni (Non-reasoning) Amazon	16.6	71.9%	-	55.5%	0.89	238	$0.30	$2.50

Showing 261-280 of 667 models