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)
Claude 4 Opus (Non-reasoning)New Anthropic	22.2	86.0%	200K	70.1%	1.41	39	$15.00	$75.00
Claude 4 Opus (Reasoning)New Anthropic	27.4	87.3%	200K	79.6%	1.35	47	$15.00	$75.00
Claude 4 Sonnet (Reasoning)New Anthropic	38.6	84.2%	1000K	77.7%	1.17	75	$3.00	$15.00
Devstral Small (Jul '25)New Mistral	15.2	62.2%	131K	41.4%	0.40	233	$0.10	$0.30
Qwen3 Omni 30B A3B InstructNew Alibaba	10.7	72.5%	131K	62.0%	0.93	89	$0.25	$0.97
Qwen3 Omni 30B A3B (Reasoning)New Alibaba	15.6	79.2%	131K	72.6%	1.12	89	$0.25	$0.97
Gemini 2.5 Flash Preview (Sep '25) (Reasoning)New Google	31.1	84.2%	1049K	79.3%	-	-	$0.30	$2.50
Nova 2.0 Omni (medium)New Amazon	27.9	80.9%	1000K	76.0%	-	-	$0.30	$2.50
Nova 2.0 Omni (low)New Amazon	23.2	79.8%	1000K	69.9%	-	-	$0.30	$2.50
Nova 2.0 Lite (Non-reasoning)New Amazon	17.9	74.3%	1000K	60.3%	0.53	184	$0.30	$2.50
Nova 2.0 Omni (Non-reasoning)New Amazon	16.6	71.9%	1000K	55.5%	0.67	207	$0.30	$2.50
Nova 2.0 Pro Preview (Non-reasoning)New Amazon	22.9	77.2%	1000K	63.6%	0.50	149	$1.25	$10.00
Nova 2.0 Pro Preview (low)New Amazon	31.9	82.2%	1000K	75.1%	12.28	129	$1.25	$10.00
Nova 2.0 Lite (medium)New Amazon	29.6	81.3%	1000K	76.8%	13.73	242	$0.30	$2.50
GPT-5 (low)New OpenAI	39.0	86.0%	400K	80.8%	27.13	87	$1.25	$10.00
Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)New Google	21.6	80.8%	1049K	70.9%	8.62	473	$0.10	$0.40
Gemma 3 4B InstructNew Google	6.3	41.7%	131K	29.1%	1.03	33	$0.00	$0.00
xAI: Grok Code Fast 1New x-ai	28.7	79.3%	256K	72.7%	7.16	268	$0.20	$1.50
Gemma 3 12B InstructNew Google	8.8	59.5%	131K	34.9%	13.68	32	$0.00	$0.00
OpenAI: GPT-5.3-CodexNew openai	-	-	400K	-	-	-	$1.75	$14.00

Showing 501-520 of 635 models