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)
GPT-5 (medium) OpenAI	42.0	86.7%	-	84.2%	42.24	73	$1.25	$10.00
MiniMax: MiniMax M2.5New MiniMax	41.9	-	197K	84.8%	1.16	75	$0.30	$1.20
DeepSeek: DeepSeek V3.2 DeepSeek	41.7	86.2%	164K	84.0%	1.46	47	$0.28	$0.42
Qwen: Qwen3.5-122B-A10BNew Alibaba	41.6	-	262K	85.7%	1.01	128	$0.40	$3.20
MiMo-V2-Flash (Feb 2026) Xiaomi	41.5	-	-	83.5%	1.52	130	$0.10	$0.30
xAI: Grok 4 xAI	41.5	86.6%	256K	87.7%	10.01	46	$3.00	$15.00
Gemini 3 Pro Preview (low) Google	41.3	89.5%	-	88.7%	-	-	$2.00	$12.00
GPT-5 mini (high) OpenAI	41.2	83.7%	-	82.8%	98.75	79	$0.25	$2.00
MoonshotAI: Kimi K2 Thinking Kimi	40.9	84.8%	262K	83.8%	0.74	84	$0.60	$2.50
OpenAI: o3 Pro OpenAI	40.7	-	200K	84.5%	91.83	19	$20.00	$80.00
Z.ai: GLM 5New Z AI	40.6	-	80K	66.6%	1.31	50	$1.00	$3.20
Qwen3.5 397B A17B (Non-reasoning)New Alibaba	40.1	-	-	86.1%	1.29	62	$0.60	$3.60
Qwen: Qwen3 Max ThinkingNew Alibaba	39.9	-	262K	86.1%	1.73	35	$1.20	$6.00
MiniMax: MiniMax M2.1 MiniMax	39.4	87.5%	197K	83.0%	1.34	79	$0.30	$1.20
Gemma 4 31B (Reasoning)New Google	39.2	-	-	85.7%	0.87	35	$0.00	$0.00
GPT-5 (low) OpenAI	39.2	86.0%	-	80.8%	9.96	71	$1.25	$10.00
MiMo-V2-Flash (Reasoning) Xiaomi	39.2	84.3%	-	84.6%	1.46	133	$0.10	$0.30
Claude 4 Opus (Reasoning) Anthropic	39.0	87.3%	-	79.6%	7.14	37	$15.00	$75.00
GPT-5 mini (medium) OpenAI	38.9	82.8%	-	80.3%	21.34	79	$0.25	$2.00
Claude 4 Sonnet (Reasoning) Anthropic	38.7	84.2%	-	77.7%	8.77	51	$3.00	$15.00

Showing 41-60 of 645 models