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	General idx ↓	Multi-IF	LiveBench	Arena Hard	Humanity’s Last Exam	IFEval	SimpleQA	MMLU-Pro	MMLU	Released	Country	Type	Access	Params	Cutoff	Context	Speed	Latency	In $/M	Out $/M
#26	o3 OpenAI	85.3	—	—	—	24.3	—	—	85.3	—	2025	—	llm	API only	—	2024	200K	50	20.00	$2.00	$8.00
#27	DeepSeek V3.1 Terminus DeepSeek	85.1	—	—	—	15.2	—	—	85.1	—	2025	—	llm	Open weights	—	2025	164K	—	—	$0.27	$0.95
#28	Kimi K2 Thinking Moonshot AI	84.8	—	—	—	22.3	—	—	84.8	—	2025	—	llm	Open weights	1T (32B active)	—	262K	100	1.00	$0.60	$2.50
#29	GLM-4.5 Zhipu AI	84.6	—	—	—	14.4	—	—	84.6	—	2025	—	llm	Open weights	355B (32B active)	2024	131K	85	0.70	$0.60	$2.20
#30	DeepSeek-R1 DeepSeek	84.4	—	—	—	9.3	—	—	84.4	90.8	2025	—	llm	Open weights	671B total / 37B active (MoE)	—	128K	189	0.07	$0.55	$2.19
#31	MiMo-V2-Flash Xiaomi	84.3	—	—	—	21.1	—	—	84.3	—	2025	—	llm	Open weights	—	—	262K	145	1.34	$0.10	$0.30
#32	Qwen3 235B A22B 2507 Alibaba	84.3	—	—	—	15	—	—	84.3	—	2025	—	llm	—	—	—	—	59	1.21	$0.40	$2.20
#33	Claude Sonnet 4 Anthropic	84.2	—	—	—	9.6	—	—	84.2	88	2025	—	llm	API only	—	2025	1M	101	0.40	$3.00	$15.00
#34	Qwen3 Max Alibaba	84.1	—	—	—	11.1	—	—	84.1	—	2025	—	llm	API only	—	2025	262K	45	1.71	$0.78	$3.90
#35	K-EXAONE LG AI Research	83.8	—	—	—	13.1	—	—	83.8	—	2025	—	llm	—	—	—	—	—	—	$0.00	$0.00
#36	GPT-5 mini OpenAI	83.7	—	—	—	16.7	—	—	83.7	—	2025	—	llm	API only	—	2024	400K	200	1.00	$0.25	$2.00
#37	Qwen3 VL 235B A22B Alibaba	83.6	—	—	—	10.1	—	—	83.6	—	2025	—	llm	—	—	—	—	34	1.75	$0.80	$6.20
#38	Llama-3.3 Nemotron Super 49B v1 NVIDIA	83.4	—	—	88.3	6.5	—	—	78.5	—	2025	—	llm	Open weights	49900000000	2023	—	—	—	$0.00	$0.00
#39	o4-mini OpenAI	83.2	—	—	—	14.7	—	—	83.2	—	2025	—	multimodal	API only	—	2024	200K	115	5.20	$1.10	$4.40
#40	Nova 2.0 Pro Amazon	83	—	—	—	8.9	—	—	83	—	2025	—	llm	—	—	—	—	149	0.81	$1.30	$10.00
#41	ERNIE 5.0 Thinking Baidu	83	—	—	—	12.7	—	—	83	—	2025	—	llm	—	—	—	—	—	—	$0.00	$0.00
#42	GLM-4.6 Zhipu AI	82.9	—	—	—	17.2	—	—	82.9	—	2025	—	llm	Open weights	357B (MoE)	2025	203K	85	0.70	$0.43	$1.74
#43	Hermes 4 - Llama-3.1 405B Nous Research	82.9	—	—	—	10.3	—	—	82.9	—	2025	—	llm	—	—	—	—	34	0.74	$1.00	$3.00
#44	Grok 3 mini Reasoning xAI	82.8	—	—	—	11.1	—	—	82.8	—	2025	—	llm	—	—	—	—	33	0.52	$0.30	$0.50
#45	Qwen3 32B Alibaba	82.8	—	74.9	93.8	8.3	—	—	79.8	—	2025	—	llm	Open weights	—	2025	131K	328	0.93	$0.08	$0.28
#46	Kimi K2 0905 Moonshot AI	82.5	—	—	—	6.3	—	—	82.5	90.2	2025	—	llm	API only	1000000000000	—	262K	16	1.94	$0.60	$2.50
#47	Qwen3 Max Thinking Alibaba	82.4	—	—	—	26.2	—	—	82.4	—	2026	—	llm	API only	—	—	262K	45	1.47	$0.78	$3.90
#48	Kimi K2 Moonshot AI	82.4	—	—	—	7	—	—	82.4	89.5	2025	—	llm	Open weights	1T (32B active)	2024	131K	26	1.51	$0.57	$2.30
#49	Qwen3-Next-80B-A3B Alibaba	82.4	—	—	—	11.7	—	—	82.4	—	2025	—	llm	Open weights	80B (3B active)	—	262K	147	1.14	$0.50	$6.00
#50	Qwen3 VL 235B A22B Instruct Alibaba	82.3	—	—	—	6.3	—	—	82.3	—	2025	—	multimodal	Open weights	—	2025	262K	51	1.20	$0.20	$0.88

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