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)
Google: Gemma 3 12B google	-	-	131K	-	-	-	$0.04	$0.13
OpenAI: GPT-5.1New openai	-	-	400K	-	0.81	94	$1.25	$10.00
GPT-5.2 Codex (xhigh)New OpenAI	49.0	-	400K	89.9%	30.08	85	$1.75	$14.00
Gemini 2.5 Flash Preview (Sep '25) (Non-reasoning)New Google	25.5	83.6%	1049K	76.6%	-	-	$0.30	$2.50
Qwen3 4B 2507 (Reasoning)New Alibaba	18.6	74.3%	41K	66.7%	-	-	$0.00	$0.00
OpenAI: GPT-5.2 ChatNew openai	-	-	128K	-	-	-	$1.75	$14.00
Gemini 2.5 Pro Preview (May' 25)New Google	29.5	83.7%	1049K	82.2%	-	-	$1.25	$10.00
Gemini 2.5 Flash Preview (Non-reasoning)New Google	17.8	78.3%	1049K	59.4%	-	-	$0.00	$0.00
Gemini 2.5 Flash Preview (Reasoning)New Google	24.3	80.0%	1049K	69.8%	-	-	$0.00	$0.00
Gemini 2.5 Pro Preview (Mar' 25)New Google	30.3	85.8%	1049K	83.6%	-	-	$0.00	$0.00
Devstral Small (May '25)New Mistral	18.0	63.2%	131K	43.4%	-	-	$0.10	$0.30
Magistral Medium 1New Mistral	18.7	75.3%	262K	67.9%	-	-	$2.00	$5.00
MoonshotAI: Kimi K2 ThinkingNew moonshotai	40.7	84.8%	131K	83.8%	0.65	72	$0.60	$2.50
Gemma 3 270MNew Google	7.5	5.5%	131K	22.4%	-	-	$0.00	$0.00
Qwen3.5 35B A3B (Reasoning)New Alibaba	37.0	-	262K	84.5%	0.96	169	$0.25	$2.00
Claude 4.5 Sonnet (Non-reasoning)New Anthropic	37.1	86.0%	1000K	72.7%	1.13	72	$3.00	$15.00
Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)New Anthropic	51.3	-	1000K	87.5%	0.88	55	$3.00	$15.00
OpenAI: GPT-5.2New openai	-	-	400K	-	0.60	73	$1.75	$14.00
DeepSeek: DeepSeek V3.2 ExpNew deepseek	-	-	164K	-	1.41	47	$0.27	$0.41
GPT-5 (minimal)New OpenAI	23.7	80.6%	400K	67.3%	1.02	67	$1.25	$10.00

Showing 461-480 of 635 models