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)
Apertus 8B Instruct Swiss AI Initiative	5.9	-	-	25.6%	-	-	$0.10	$0.20
Qwen3 0.6B (Non-reasoning) Alibaba	5.7	23.1%	-	23.1%	0.90	193	$0.11	$0.42
Gemma 3 1B Instruct Google	5.5	13.5%	-	23.7%	0.57	41	$0.00	$0.00
Granite 4.0 H 350M IBM	5.4	12.7%	-	25.7%	-	-	$0.00	$0.00
Gemma 3n E2B Instruct Google	4.8	37.8%	-	22.9%	0.40	41	$0.00	$0.00
Tiny Aya GlobalNew Cohere	4.7	-	-	30.5%	-	-	$0.00	$0.00
AI21: Jamba Large 1.7 AI21	-	-	256K	-	-	-	$2.00	$8.00
AionLabs: Aion-1.0 AionLabs	-	-	131K	-	-	-	$4.00	$8.00
AionLabs: Aion-1.0-Mini AionLabs	-	-	131K	-	-	-	$0.70	$1.40
AionLabs: Aion-2.0 AionLabs	-	-	131K	-	-	-	$0.80	$1.60
AionLabs: Aion-RP 1.0 (8B) AionLabs	-	-	33K	-	-	-	$0.80	$1.60
AlfredPros: CodeLLaMa 7B Instruct Solidity AlfredPros	-	-	4K	-	-	-	$0.80	$1.20
AllenAI: Olmo 2 32B Instruct AllenAI	-	-	128K	-	-	-	$0.05	$0.20
Amazon: Nova 2 Lite Amazon	-	-	1000K	-	-	-	$0.30	$2.50
Amazon: Nova Lite 1.0 Amazon	-	-	300K	-	-	-	$0.06	$0.24
Amazon: Nova Micro 1.0 Amazon	-	-	128K	-	-	-	$0.04	$0.14
Amazon: Nova Premier 1.0 Amazon	-	-	1000K	-	-	-	$2.50	$12.50
Amazon: Nova Pro 1.0 Amazon	-	-	300K	-	-	-	$0.80	$3.20
Anthropic: Claude Haiku 4.5 Anthropic	-	-	200K	-	-	-	$1.00	$5.00
Anthropic: Claude Opus 4 Anthropic	-	-	200K	-	-	-	$15.00	$75.00

Showing 461-480 of 645 models