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)
Anthropic: Claude Sonnet 4.6New anthropic	-	-	1000K	-	-	-	$3.00	$15.00
Anthropic: Claude Opus 4.6New anthropic	-	-	1000K	-	-	-	$5.00	$25.00
OpenAI: GPT-5.2-CodexNew openai	-	-	400K	-	-	-	$1.75	$14.00
OpenAI: GPT-5.1-Codex-MaxNew openai	-	-	400K	-	-	-	$1.25	$10.00
DeepSeek: DeepSeek V3.2 SpecialeNew deepseek	-	-	164K	-	-	-	$0.40	$1.20
Claude 4 Sonnet (Non-reasoning)New Anthropic	33.0	83.7%	1000K	68.3%	1.27	64	$3.00	$15.00
Claude 4.1 Opus (Non-reasoning)New Anthropic	23.6	-	200K	-	1.33	39	$15.00	$75.00
DeepSeek: DeepSeek V3.2New deepseek	-	-	164K	-	1.29	46	$0.25	$0.40
Claude Opus 4.6 (Non-reasoning, High Effort)New Anthropic	46.4	-	1000K	84.0%	1.70	67	$5.00	$25.00
OpenAI: GPT-5.1-CodexNew openai	-	-	400K	-	-	-	$1.25	$10.00
OpenAI: GPT-5 Image MiniNew openai	-	-	400K	-	-	-	$2.50	$2.00
GPT-5 mini (high)New OpenAI	41.0	83.7%	400K	82.8%	99.88	74	$0.25	$2.00
GPT-5.1 Codex mini (high)New OpenAI	38.5	82.0%	400K	81.3%	11.62	149	$0.25	$2.00
GPT-5.2 (medium)New OpenAI	46.6	85.9%	400K	86.4%	-	-	$1.75	$14.00
GPT-5.2 (xhigh)New OpenAI	51.2	87.4%	400K	90.3%	38.29	87	$1.75	$14.00
Claude 4.5 Haiku (Reasoning)New Anthropic	37.0	76.0%	200K	67.2%	0.47	121	$1.00	$5.00
Claude Sonnet 4.6 (Non-reasoning, Low Effort)New Anthropic	42.5	-	1000K	79.7%	0.95	61	$3.00	$15.00
Devstral 2New Mistral	22.0	76.2%	131K	59.4%	0.39	77	$0.00	$0.00
Devstral Small 2New Mistral	19.3	67.8%	131K	53.2%	0.38	201	$0.00	$0.00
Magistral Small 1.2New Mistral	18.1	76.8%	262K	66.3%	0.34	214	$0.50	$1.50

Showing 521-540 of 635 models