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	Coding idx ↓	SciCode	Aider Polyglot Edit	MultiPL-E	MBPP	SWE-bench Pro	Aider Polyglot	LiveCodeBench	Terminal-Bench	SWE-bench Verified	HumanEval	Released	Country	Type	Access	Params	Cutoff	Context	Speed	Latency	In $/M	Out $/M
#201	Kimi Linear 48B A3B Instruct Moonshot AI	23	19.9	—	—	—	—	—	37.8	11.4	—	—	2025	—	llm	—	—	—	—	—	—	$0.00	$0.00
#202	JT-MINI China Mobile	22.7	27.2	—	—	—	—	—	—	18.2	—	—	2026	—	llm	—	—	—	—	—	—	$0.00	$0.00
#203	Llama 3.1 405B Instruct Meta	22.4	29.9	—	—	—	—	—	30.5	6.8	—	89	2024	—	llm	Open weights	405000000000	—	128K	100	0.40	$0.89	$0.89
#204	Nova Premier Amazon	22.1	27.9	—	—	—	—	—	31.7	6.8	—	—	2025	—	llm	—	—	—	—	40	1.31	$2.50	$12.50
#205	Qwen3 8B Alibaba	21.8	22.6	—	—	—	—	—	40.6	2.3	—	—	2025	—	llm	Open weights	—	2025	131K	69	1.29	$0.05	$0.40
#206	Mistral Large 2 Mistral AI	21.5	29.2	—	—	—	—	—	29.3	6.1	—	92	2024	—	llm	Open weights	123B	—	128K	42	0.40	$2.00	$6.00
#207	Ministral 3 14B Mistral AI	21.1	23.6	—	—	—	—	—	35.1	4.5	—	—	2025	—	multimodal	Open weights	—	—	262K	67	0.41	$0.20	$0.20
#208	Qwen3 Omni 30B A3B Instruct Alibaba	20.8	18.6	—	—	—	—	—	42.2	1.5	—	—	2025	—	llm	—	—	—	—	103	1.04	$0.30	$1.00
#209	Qwen3 VL 8B Alibaba	20.3	21.9	—	—	—	—	—	35.3	3.8	—	—	2025	—	llm	—	—	—	—	120	1.15	$0.20	$2.10
#210	Exaone 4.0 1.2B LG AI Research	20.3	9.3	—	—	—	—	—	51.6	0	—	—	2025	—	llm	—	—	—	—	—	—	$0.00	$0.00
#211	Mistral Small 3.2 Mistral AI	20.2	26.4	—	—	—	—	—	27.5	6.8	—	—	2025	—	llm	—	—	—	—	100	0.40	$0.10	$0.30
#212	Qwen3 4B 2507 Instruct Alibaba	20.1	18.1	—	—	—	—	—	37.7	4.5	—	—	2025	—	llm	—	—	—	—	—	—	$0.00	$0.00
#213	K2 Think V2 MBZUAI Institute of Foundation Models	19.9	33	—	—	—	—	—	—	6.8	—	—	2025	—	llm	—	—	—	—	—	—	$0.00	$0.00
#214	LongCat Flash Lite LongCat	19.5	28.4	—	—	—	—	—	—	10.6	—	—	2026	—	llm	—	—	—	—	110	5.59	$0.00	$0.00
#215	Llama 3.3 70B Instruct Meta	19.3	26	—	—	—	—	—	28.8	3	—	88.4	2024	—	llm	Open weights	—	2023	131K	2220	0.50	$0.10	$0.32
#216	Ling-mini-2.0 InclusionAI	19.1	13.5	—	—	—	—	—	42.9	0.8	—	—	2025	—	llm	—	—	—	—	—	—	$0.00	$0.00
#217	Devstral Small Mistral AI	18.8	24.5	—	—	—	—	—	25.8	6.1	—	—	2025	—	llm	—	—	—	—	190	0.42	$0.10	$0.30
#218	Llama-3.3 Nemotron Super 49B v1 NVIDIA	18.7	28.2	—	—	91.3	—	—	28	0	—	—	2025	—	llm	Open weights	49900000000	2023	—	—	—	$0.00	$0.00
#219	Ministral 3 8B Mistral AI	18.5	20.8	—	—	—	—	—	30.3	4.5	—	—	2025	—	multimodal	Open weights	—	—	262K	86	0.38	$0.15	$0.15
#220	Mistral Small 3.1 Mistral AI	18.4	26.5	—	—	—	—	—	21.2	7.6	—	—	2025	—	llm	—	—	—	—	134	0.52	$0.10	$0.20
#221	Qwen3.5 4B Alibaba	18.3	18.3	—	—	—	—	—	—	18.2	—	—	2026	—	llm	—	—	—	—	164	0.24	$0.00	$0.20
#222	Step3 VL 10B StepFun	18.2	31.1	—	—	—	—	—	—	5.3	—	—	2026	—	llm	—	—	—	—	—	—	$0.00	$0.00
#223	Nemotron 3 Nano Omni 30B A3B Reasoning NVIDIA	18.1	27.8	—	—	—	—	—	—	8.3	—	—	2026	—	llm	—	—	—	—	301	0.58	$0.10	$0.30
#224	Llama 3.1 70B Instruct Meta	17.6	26.7	—	—	—	—	—	23.2	3	—	80.5	2024	—	llm	Open weights	—	2023	131K	1204	0.20	$0.40	$0.40
#225	Qwen3 VL 8B Instruct Alibaba	17.6	17.4	—	—	—	—	—	33.2	2.3	—	—	2025	—	multimodal	Open weights	—	—	256K	145	1.05	$0.08	$0.50

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