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 (high) OpenAI	44.6	87.1%	-	85.4%	92.98	107	$1.25	$10.00
OpenAI: GPT-5 Codex OpenAI	44.6	86.5%	400K	83.7%	8.78	207	$1.25	$10.00
Anthropic: Claude Sonnet 4.6New Anthropic	44.4	-	1000K	79.9%	0.96	60	$3.00	$15.00
OpenAI: GPT-5.4 NanoNew OpenAI	44.0	-	400K	81.7%	3.35	149	$0.20	$1.25
GLM-5.1 (Non-reasoning)New Z AI	43.8	-	-	83.9%	1.21	50	$1.40	$4.40
Kwaipilot: KAT-Coder-Pro V2New KwaiKAT	43.8	-	256K	85.5%	1.87	115	$0.30	$1.20
Qwen3.6 35B A3B (Reasoning)New Alibaba	43.5	-	-	84.1%	1.43	200	$0.38	$2.25
Xiaomi: MiMo-V2-OmniNew Xiaomi	43.4	-	262K	82.8%	-	-	$0.00	$0.00
Anthropic: Claude Opus 4.5 Anthropic	43.1	88.9%	200K	81.0%	1.44	64	$5.00	$25.00
OpenAI: GPT-5.1-Codex OpenAI	43.1	86.0%	400K	86.0%	3.83	179	$1.25	$10.00
Claude 4.5 Sonnet (Reasoning) Anthropic	43.0	87.5%	-	83.4%	7.61	64	$3.00	$15.00
Z.ai: GLM 5V TurboNew Z AI	42.9	-	203K	80.9%	-	-	$0.00	$0.00
Claude Sonnet 4.6 (Non-reasoning, Low Effort)New Anthropic	42.6	-	-	79.7%	1.11	61	$3.00	$15.00
GLM-4.7 (Reasoning) Z AI	42.1	85.6%	-	85.9%	0.78	85	$0.60	$2.20
Qwen: Qwen3.5-27BNew Alibaba	42.1	-	262K	85.8%	1.53	91	$0.30	$2.40
Claude 4.1 Opus (Reasoning) Anthropic	42.0	88.0%	-	80.9%	8.84	45	$15.00	$75.00
GPT-5 (medium) OpenAI	42.0	86.7%	-	84.2%	45.35	84	$1.25	$10.00
MiniMax: MiniMax M2.5New MiniMax	41.9	-	197K	84.8%	1.17	99	$0.30	$1.20
DeepSeek V3.2 (Reasoning) DeepSeek	41.7	86.2%	-	84.0%	0.94	79	$0.28	$0.42
Qwen: Qwen3.5-122B-A10BNew Alibaba	41.6	-	262K	85.7%	1.09	154	$0.40	$3.20

Showing 41-60 of 667 models