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)
Mistral Small (Feb '24) Mistral	9.0	41.9%	131K	30.2%	0.31	138	$1.00	$3.00
DeepSeek R1 0528 Qwen3 8B DeepSeek	16.4	73.9%	164K	61.2%	-	-	$0.00	$0.00
MiniMax-M2.1 MiniMax	39.5	87.5%	197K	83.0%	3.25	55	$0.30	$1.20
MiniMax-M2 MiniMax	36.0	82.0%	197K	77.7%	2.46	52	$0.30	$1.20
GLM-4.7 (Reasoning) Z AI	42.0	85.6%	203K	85.9%	0.63	109	$0.55	$2.15
GLM-4.7 (Non-reasoning) Z AI	34.1	79.4%	203K	66.4%	0.55	119	$0.55	$2.15
GLM-4.6 (Non-reasoning) Z AI	30.1	78.4%	203K	63.2%	0.76	76	$0.60	$2.20
Hermes 3 - Llama-3.1 70B Nous Research	10.6	57.1%	131K	40.1%	0.48	35	$0.30	$0.30
Nova Lite Amazon	12.4	59.0%	300K	43.3%	0.40	220	$0.06	$0.24
Solar Mini Upstage	8.0	-	33K	-	1.39	82	$0.15	$0.15
Granite 3.3 8B (Non-reasoning) IBM	6.8	46.8%	128K	33.8%	20.50	529	$0.03	$0.25
Reka Flash (Sep '24) Reka AI	12.0	-	128K	-	1.31	68	$0.20	$0.80
Qwen: Qwen3.5-35B-A3B qwen	-	-	262K	-	-	-	$0.25	$2.00
Qwen: Qwen3.5-27B qwen	-	-	262K	-	-	-	$0.30	$2.40
Kimi K2New Kimi	26.2	82.4%	131K	76.6%	0.56	41	$0.60	$2.50
Gemma 3n E2B InstructNew Google	4.7	37.8%	33K	22.9%	0.38	49	$0.00	$0.00
Gemini 3 Pro Preview (low)New Google	41.1	89.5%	1049K	88.7%	4.08	137	$2.00	$12.00
Jamba 1.6 Mini AI21 Labs	7.9	36.7%	256K	30.0%	0.65	176	$0.20	$0.40
Jamba 1.6 Large AI21 Labs	10.6	56.5%	256K	38.7%	0.85	52	$2.00	$8.00
GLM-4.6 (Reasoning) Z AI	32.5	82.9%	203K	78.0%	0.58	97	$0.57	$2.20

Showing 361-380 of 635 models