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)
DeepSeek V3.2 (Non-reasoning) DeepSeek	32.1	83.7%	-	75.1%	1.43	47	$0.28	$0.42
Grok 3 mini Reasoning (high) xAI	32.1	82.8%	-	79.1%	0.36	197	$0.30	$0.50
K-EXAONE (Reasoning) LG AI Research	32.1	83.8%	-	78.3%	-	-	$0.00	$0.00
Arcee AI: Trinity Large ThinkingNew Arcee AI	31.9	-	262K	75.2%	0.60	118	$0.23	$0.88
Nova 2.0 Pro Preview (low) Amazon	31.9	82.2%	-	75.1%	5.07	151	$1.25	$10.00
Qwen: Qwen3 Max Alibaba	31.4	84.1%	262K	76.4%	1.84	33	$1.20	$6.00
Google: Gemma 4 26B A4B New Google	31.2	-	262K	79.2%	-	-	$0.13	$0.40
Claude 4.5 Haiku (Non-reasoning) Anthropic	31.1	80.0%	-	64.6%	0.57	103	$1.00	$5.00
Gemini 2.5 Flash Preview (Sep '25) (Reasoning) Google	31.1	84.2%	-	79.3%	-	-	$0.00	$0.00
MoonshotAI: Kimi K2 0905 Kimi	30.9	81.9%	262K	76.7%	0.68	50	$0.80	$2.25
Anthropic: Claude 3.7 Sonnet Anthropic	30.8	80.3%	200K	65.6%	-	-	$3.00	$15.00
OpenAI: o1 OpenAI	30.8	84.1%	200K	74.7%	20.18	100	$15.00	$60.00
Qwen: Qwen3.5-35B-A3BNew Alibaba	30.7	-	262K	81.9%	1.02	134	$0.25	$2.00
Xiaomi: MiMo-V2-Flash Xiaomi	30.4	74.4%	262K	65.6%	1.31	134	$0.10	$0.30
Gemini 2.5 Pro Preview (Mar' 25) Google	30.3	85.8%	-	83.6%	-	-	$0.00	$0.00
Z.ai: GLM 4.6 Z AI	30.2	78.4%	205K	63.2%	0.80	74	$0.60	$2.20
GLM-4.7-Flash (Reasoning)New Z AI	30.1	-	-	58.1%	0.75	85	$0.07	$0.40
Grok 4.20 0309 (Non-reasoning)New xAI	29.7	-	-	78.5%	0.31	181	$2.00	$6.00
Nova 2.0 Lite (medium) Amazon	29.7	81.3%	-	76.8%	20.41	229	$0.30	$2.50
Gemini 2.5 Pro Preview (May' 25) Google	29.5	83.7%	-	82.2%	-	-	$1.25	$10.00

Showing 101-120 of 645 models