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)
Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)New Anthropic	48.4	-	-	87.5%	-	-	$3.00	$15.00
MoonshotAI: Kimi K3New Kimi	48.3	-	1049K	84.2%	2.57	39	$3.00	$15.00
Google: Gemini 3.1 Pro PreviewNew Google	47.7	-	1049K	94.1%	29.85	124	$2.00	$12.00
Motif 3New Motif Technologies	47.4	-	-	83.4%	-	-	$0.00	$0.00
GPT-5.6 Luna (high)New OpenAI	47.0	-	-	89.2%	10.89	139	$0.20	$1.20
GPT-5.6 Terra (medium)New OpenAI	46.8	-	-	87.2%	1.66	99	$2.00	$12.00
Google: Gemini 3.5 FlashNew Google	46.7	-	1049K	92.1%	11.33	256	$1.50	$9.00
Qwen: Qwen3.7 MaxNew Alibaba	46.7	-	1000K	92.3%	-	-	$2.50	$7.50
OpenAI: GPT-5.3-CodexNew OpenAI	45.5	-	400K	91.5%	45.56	125	$1.75	$14.00
MiniMax: MiniMax M3New MiniMax	45.4	-	1049K	92.9%	1.53	108	$0.30	$1.20
DeepSeek V4 Pro (Reasoning, Max Effort)New DeepSeek	45.3	-	-	88.8%	1.36	66	$0.43	$0.87
Motif 3 (Beta)New Motif Technologies	45.3	-	-	86.9%	-	-	$0.00	$0.00
MoonshotAI: Kimi K2.6New Kimi	45.1	-	262K	91.1%	-	-	$0.95	$4.00
Claude Opus 4.6 (Adaptive Reasoning, Max Effort)New Anthropic	44.9	-	-	89.6%	-	-	$5.00	$25.00
GPT-5.5 (low)New OpenAI	44.5	-	-	91.0%	-	-	$5.00	$30.00
Muse SparkNew Meta	44.3	-	-	88.4%	-	-	$0.00	$0.00
Claude Opus 4.7 (Non-reasoning, High Effort)New Anthropic	43.9	-	-	88.5%	-	-	$5.00	$25.00
DeepSeek V4 Pro (Reasoning, High Effort)New DeepSeek	43.7	-	-	90.5%	1.17	71	$0.43	$0.87
OpenAI: GPT-5.2 OpenAI	43.3	87.4%	400K	90.3%	-	-	$1.75	$14.00
MoonshotAI: Kimi K2.7 CodeNew Kimi	43.0	-	262K	89.6%	1.57	38	$0.95	$4.00

Showing 41-60 of 835 models