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	Agents idx ↓	τ²-bench	BFCL	τ²-bench Airline	τ²-bench Retail	BrowseComp	TAU-bench Airline	TAU-bench Retail	Released	Country	Type	Access	Params	Cutoff	Context	Speed	Latency	In $/M	Out $/M
#201	Qwen3 1.7B Alibaba	26	26	—	—	—	—	—	—	2025	—	llm	—	—	—	—	138	0.97	$0.10	$0.40
#202	K2 Think V2 MBZUAI Institute of Foundation Models	25.4	25.4	—	—	—	—	—	—	2025	—	llm	—	—	—	—	—	—	$0.00	$0.00
#203	Qwen3 4B 2507 Alibaba	25.4	25.4	—	—	—	—	—	—	2025	—	llm	—	—	—	—	—	—	$0.00	$0.00
#204	Mistral Small 3.1 Mistral AI	25.1	25.1	—	—	—	—	—	—	2025	—	llm	—	—	—	—	134	0.52	$0.10	$0.20
#205	Devstral 2 Mistral AI	24.9	24.9	—	—	—	—	—	—	2025	—	llm	Open weights	—	—	262K	51	0.64	$0.40	$2.00
#206	Ministral 3 3B Mistral AI	24.9	24.9	—	—	—	—	—	—	2025	—	multimodal	Open weights	—	—	131K	154	0.34	$0.10	$0.10
#207	Mistral Large 3 Mistral AI	24.6	24.6	—	—	—	—	—	—	2025	—	llm	Open weights	675B (41B active)	—	262K	54	0.64	$0.50	$1.50
#208	Mistral Medium 3 Mistral AI	24.3	24.3	—	—	—	—	—	—	2025	—	multimodal	API only	—	2025	131K	32	0.56	$0.40	$2.00
#209	Devstral Small 2 Mistral AI	23.4	23.4	—	—	—	—	—	—	2025	—	llm	—	—	—	—	62	0.75	$0.00	$0.00
#210	NVIDIA Nemotron Nano 9B V2 NVIDIA	23.4	23.4	—	—	—	—	—	—	2025	—	llm	—	—	—	—	129	0.26	$0.00	$0.20
#211	Qwen3 VL 4B Instruct Alibaba	23.4	23.4	—	—	—	—	—	—	2025	—	llm	—	—	—	—	—	—	$0.00	$0.00
#212	Magistral Medium 1 Mistral AI	23.1	23.1	—	—	—	—	—	—	2025	—	llm	—	—	—	—	—	—	$0.00	$0.00
#213	Llama 3.1 Nemotron 70B Instruct NVIDIA	23.1	23.1	—	—	—	—	—	—	2024	—	llm	Open weights	70000000000	2023	—	292	0.24	$1.20	$1.20
#214	DeepSeek-V3 DeepSeek	22.8	22.8	—	—	—	—	—	—	2024	—	llm	Open weights	671B total / 37B active (MoE)	2024	131K	100	0.50	$0.23	$0.91
#215	Granite 4.0 1B IBM	22.8	22.8	—	—	—	—	—	—	2025	—	llm	—	—	—	—	—	—	$0.00	$0.00
#216	DeepSeek-R1-0528 DeepSeek	22.7	36.5	—	—	—	8.9	—	—	2025	—	llm	Open weights	671000000000	—	131K	45	0.30	$0.55	$2.19
#217	Qwen3 VL 8B Alibaba	22.5	22.5	—	—	—	—	—	—	2025	—	llm	—	—	—	—	120	1.15	$0.20	$2.10
#218	Hermes 4 - Llama-3.1 70B Nous Research	22.5	22.5	—	—	—	—	—	—	2025	—	llm	—	—	—	—	60	0.67	$0.10	$0.40
#219	GLM 4.5V Zhipu AI	22.5	22.5	—	—	—	—	—	—	2025	—	multimodal	Open weights	—	2024	66K	85	0.70	$0.60	$1.80
#220	Gemma 4 E2B Google	22.2	22.2	—	—	—	—	—	—	2026	—	llm	—	—	—	—	—	—	$0.00	$0.00
#221	DeepSeek R1 Distill Llama 70B DeepSeek	21.9	21.9	—	—	—	—	—	—	2025	—	llm	Open weights	70600000000	—	128K	37	0.65	$0.10	$0.40
#222	Nanbeige4.1-3B Nanbeige	21.6	21.6	—	—	—	—	—	—	2026	—	llm	—	—	—	—	—	—	$0.00	$0.00
#223	NVIDIA Nemotron Nano 12B v2 VL NVIDIA	21.3	21.3	—	—	—	—	—	—	2025	—	llm	—	—	—	—	244	0.74	$0.20	$0.60
#224	Qwen3 Omni 30B A3B Alibaba	21.3	21.3	—	—	—	—	—	—	2025	—	llm	—	—	—	—	102	1.05	$0.30	$1.00
#225	Olmo 3.1 32B Instruct Allen Institute for AI	21.3	21.3	—	—	—	—	—	—	2026	—	llm	—	—	—	—	—	—	$0.00	$0.00

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