298 models in catalog

AI models

Every model we track — frontier flagships, open-weights specialists, narrow benchmarks-only releases. Filter by lab, country, access, modality, or release window. Sorted by newest by default; head to the leaderboard for the ranked view.

Leaderboard →Labs →Benchmarks →

Updated May 29, 2026 · Benchmarks via Artificial Analysis, specs & pricing via OpenRouter · Methodology · Spotted an error?

Overview Reasoning Coding Math Agents Multimodal General Long Context

Rank	Model	Math idx ↓	MATH-500	FrontierMath	HMMT 2025	GSM8K	MGSM	AIME 2024	AIME 2025	MATH	Released	Country	Type	Access	Params	Cutoff	Context	Speed	Latency	In $/M	Out $/M
#26	NVIDIA Nemotron 3 Nano 30B A3B NVIDIA	91	—	—	—	—	—	—	91	—	2025	—	llm	—	—	—	—	148	0.30	$0.10	$0.20
#27	K-EXAONE LG AI Research	90.3	—	—	—	—	—	—	90.3	—	2025	—	llm	—	—	—	—	—	—	$0.00	$0.00
#28	Nova 2.0 Omni Amazon	89.7	—	—	—	—	—	—	89.7	—	2025	—	llm	—	—	—	—	—	—	$0.30	$2.50
#29	DeepSeek V3.1 Terminus DeepSeek	89.7	—	—	—	—	—	—	89.7	—	2025	—	llm	Open weights	—	2025	164K	—	—	$0.27	$0.95
#30	GLM 4.5 Air Zhipu AI	89.4	98.1	—	—	—	—	89.4	80.7	—	2025	—	llm	Open weights	—	2024	131K	63	1.68	$0.13	$0.85
#31	Grok 4.1 Fast xAI	89.3	—	—	—	—	—	—	89.3	—	2025	—	llm	—	—	—	—	—	—	$0.00	$0.00
#32	gpt-oss-20b OpenAI	89.3	—	—	—	—	—	—	89.3	—	2025	—	llm	Open weights	21B (3.6B active)	2024	131K	1000	0.38	$0.03	$0.14
#33	Ring-1T InclusionAI	89.3	—	—	—	—	—	—	89.3	—	2025	—	llm	—	—	—	—	—	—	$0.00	$0.00
#34	DeepSeek-R1-0528 DeepSeek	89.2	98.3	—	79.4	—	—	91.4	87.5	—	2025	—	llm	Open weights	671000000000	—	131K	45	0.30	$0.55	$2.19
#35	Nova 2.0 Pro Amazon	89	—	—	—	—	—	—	89	—	2025	—	llm	—	—	—	—	149	0.81	$1.30	$10.00
#36	EXAONE 4.0 32B LG AI Research	88.9	97.7	—	—	—	—	—	80	—	2025	—	llm	—	—	—	—	—	—	$0.00	$0.00
#37	Qwen3 VL 235B A22B Alibaba	88.3	—	—	—	—	—	—	88.3	—	2025	—	llm	—	—	—	—	34	1.75	$0.80	$6.20
#38	Gemini 2.5 Flash Google	88.1	98.1	—	—	—	—	88	78.3	—	2025	—	multimodal	API only	—	2025	1M	85	0.70	$0.30	$2.50
#39	Apriel-v1.6-15B-Thinker ServiceNow	88	—	—	—	—	—	—	88	—	2025	—	llm	—	—	—	—	—	—	$0.00	$0.00
#40	INTELLECT-3 Prime Intellect	88	—	—	—	—	—	—	88	—	2025	—	llm	Open weights	—	—	131K	—	—	$0.20	$1.10
#41	GLM-4.5 Zhipu AI	87.6	98.2	—	—	—	—	91	73.7	—	2025	—	llm	Open weights	355B (32B active)	2024	131K	85	0.70	$0.60	$2.20
#42	Apriel-v1.5-15B-Thinker ServiceNow	87.5	—	—	—	—	—	—	87.5	—	2025	—	llm	—	—	—	—	—	—	$0.00	$0.00
#43	Llama Nemotron Super 49B v1.5 NVIDIA	87.5	98.3	—	—	—	—	—	76.7	—	2025	—	llm	—	—	—	—	51	0.29	$0.10	$0.40
#44	Claude Sonnet 4.5 Anthropic	87	—	—	—	—	—	—	87	—	2025	—	llm	API only	—	2025	1M	42	0.40	$3.00	$15.00
#45	Claude Opus 4 Anthropic	86.9	98.2	—	—	—	—	—	75.5	—	2025	—	llm	API only	—	2025	200K	120	0.40	$15.00	$75.00
#46	Qwen3 235B A22B Alibaba	86.7	93	—	—	94.4	83.5	85.7	81.5	71.8	2025	—	llm	Open weights	—	2025	131K	68	0.78	$0.46	$1.82
#47	DeepSeek V3.2 Exp DeepSeek	86.4	—	—	83.6	—	—	—	89.3	—	2025	—	llm	Open weights	—	2025	164K	100	0.70	$0.27	$0.41
#48	GLM 4.6V Zhipu AI	85.3	—	—	—	—	—	—	85.3	—	2025	—	multimodal	Open weights	—	—	131K	44	1.31	$0.30	$0.90
#49	ERNIE 5.0 Thinking Baidu	85	—	—	—	—	—	—	85	—	2025	—	llm	—	—	—	—	—	—	$0.00	$0.00
#50	Claude Sonnet 4 Anthropic	84.8	99.1	—	—	—	—	—	70.5	—	2025	—	llm	API only	—	2025	1M	101	0.40	$3.00	$15.00

Ranked on Math. Cell colors show relative standing within each column (red → yellow → green). Scores are curated approximations — see each model for sources.