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)
Grok 3 Reasoning Beta SpaceXAI Intelligence: 15.2Input (1M): $0.00	15.2	-	-	-	-	-	$0.00	$0.00
OpenAI: gpt-oss-20b OpenAI Intelligence: 15.2Input (1M): $0.06	15.2	74.8%	131K	68.8%	0.47	148	$0.06	$0.19
Solar Open 100B (Reasoning) Upstage Intelligence: 15.2Input (1M): $0.00	15.2	-	-	65.7%	-	-	$0.00	$0.00
Nemotron 3 Nano Omni 30B A3B ReasoningNew NVIDIA Intelligence: 15.0Input (1M): $0.07	15.0	-	-	46.9%	0.57	327	$0.07	$0.30
gpt-oss-120b (low) OpenAI Intelligence: 14.9Input (1M): $0.15	14.9	77.5%	-	67.2%	0.54	159	$0.15	$0.59
Mistral Small 3.1 Mistral Intelligence: 14.9Input (1M): $0.10	14.9	65.9%	-	45.4%	-	-	$0.10	$0.30
OpenAI: GPT-4.1 Mini OpenAI Intelligence: 14.8Input (1M): $0.40	14.8	78.1%	1048K	66.4%	-	-	$0.40	$1.60
Mistral: Mistral Medium 3.1 Mistral Intelligence: 14.7Input (1M): $0.40	14.7	68.3%	131K	58.8%	-	-	$0.40	$2.00
Qwen3 30B A3B 2507 (Reasoning) Alibaba Intelligence: 14.6Input (1M): $0.20	14.6	80.5%	-	70.7%	-	-	$0.20	$2.40
Meta: Llama 4 Maverick Meta Intelligence: 14.5Input (1M): $0.26	14.5	80.9%	1049K	67.1%	0.58	85	$0.26	$0.91
MiniMax M1 40k MiniMax Intelligence: 14.5Input (1M): $0.00	14.5	80.8%	-	68.2%	-	-	$0.00	$0.00
NVIDIA: Nemotron 3 Nano 30B A3B NVIDIA Intelligence: 14.5Input (1M): $0.05	14.5	79.4%	262K	75.7%	0.67	191	$0.05	$0.20
Upstage: Solar Pro 3New Upstage Intelligence: 14.5Input (1M): $0.15	14.5	-	131K	72.4%	1.14	142	$0.15	$0.60
gpt-oss-20b (low) OpenAI Intelligence: 14.4Input (1M): $0.07	14.4	71.8%	-	61.1%	0.57	182	$0.07	$0.20
Nova 2.0 Pro Preview (Non-reasoning) Amazon Intelligence: 14.4Input (1M): $1.25	14.4	77.2%	-	63.6%	0.69	125	$1.25	$10.00
Qwen: Qwen3 VL 235B A22B Instruct Alibaba Intelligence: 14.4Input (1M): $0.40	14.4	82.3%	262K	71.2%	-	-	$0.40	$1.60
GPT-5 mini (minimal) OpenAI Intelligence: 14.3Input (1M): $0.25	14.3	77.5%	-	68.7%	-	-	$0.25	$2.00
Granite 4.2 3BNew IBM Intelligence: 14.3Input (1M): $0.03	14.3	-	-	55.9%	0.20	223	$0.03	$0.12
DeepSeek V3 (Dec '24) DeepSeek Intelligence: 14.2Input (1M): $0.36	14.2	75.2%	-	55.7%	-	-	$0.36	$0.89
Google: Gemini 2.5 Flash Google Intelligence: 14.2Input (1M): $0.30	14.2	80.9%	1049K	68.3%	-	-	$0.30	$2.50

Showing 341-360 of 793 models