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
#151	Nova Pro Amazon	42.8	78.6	—	—	94.8	—	—	7	76.6	2024	—	multimodal	API only	—	—	300K	100	0.50	$0.80	$3.20
#152	GPT-4o OpenAI	42.7	89.3	—	—	—	—	13.1	25.7	—	2024	—	multimodal	API only	—	2023	128K	132	0.50	$2.50	$10.00
#153	Llama 3.3 70B Instruct Meta	42.5	77.3	—	—	—	91.1	—	7.7	77	2024	—	llm	Open weights	—	2023	131K	2220	0.50	$0.10	$0.32
#154	Llama 3.1 Nemotron 70B Instruct NVIDIA	42.2	73.3	—	—	91.4	—	—	11	—	2024	—	llm	Open weights	70000000000	2023	—	292	0.24	$1.20	$1.20
#155	Nova Lite Amazon	41.8	76.5	—	—	94.5	—	—	7	73.3	2024	—	multimodal	API only	—	—	300K	100	0.50	$0.06	$0.24
#156	Olmo 3 7B Instruct Allen Institute for AI	41.3	—	—	—	—	—	—	41.3	—	2025	—	llm	—	—	—	—	—	—	$0.10	$0.20
#157	Gemma 3n E2B Instruct Google	39.7	69.1	—	—	—	—	—	10.3	—	2025	—	llm	—	—	—	—	—	—	$0.00	$0.00
#158	Claude 3 Haiku Anthropic	39.4	39.4	—	—	88.9	75.1	—	—	38.9	2024	—	multimodal	API only	—	2023	200K	104	0.40	$0.25	$1.25
#159	Mistral Medium 3.1 Mistral AI	38.3	—	—	—	—	—	—	38.3	—	2025	—	multimodal	API only	—	2025	131K	47	0.69	$0.40	$2.00
#160	Nova Micro Amazon	38.2	70.3	—	—	92.3	—	—	6	69.3	2024	—	llm	API only	—	—	128K	100	0.50	$0.03	$0.14
#161	Phi 4 Mini Instruct Microsoft	38.2	69.6	—	—	—	—	—	6.7	—	2025	—	llm	Open weights	—	—	131K	—	—	$0.08	$0.35
#162	Mistral Large 3 Mistral AI	38	—	—	—	—	—	—	38	—	2025	—	llm	Open weights	675B (41B active)	—	262K	54	0.64	$0.50	$1.50
#163	Mistral Small 3 Mistral AI	37.9	71.5	—	—	—	—	—	4.3	—	2025	—	llm	Open weights	—	2023	33K	136	0.53	$0.05	$0.08
#164	Devstral Medium Mistral AI	37.7	70.7	—	—	—	—	—	4.7	—	2025	—	llm	API only	—	2025	131K	72	0.49	$0.40	$2.00
#165	Mistral Small 3.1 Mistral AI	37.2	70.7	—	—	—	—	—	3.7	—	2025	—	llm	—	—	—	—	134	0.52	$0.10	$0.20
#166	Qwen3 VL 4B Instruct Alibaba	37	—	—	—	—	—	—	37	—	2025	—	llm	—	—	—	—	—	—	$0.00	$0.00
#167	Pixtral Large Mistral AI	36.9	71.4	—	—	—	—	—	2.3	—	2024	—	multimodal	API only	—	2024	131K	0	0.50	$2.00	$6.00
#168	GPT-4.5 OpenAI	36.7	—	—	—	97	—	36.7	—	85	2025	—	multimodal	API only	—	—	128K	50	20.00	$75.00	$150.00
#169	Llama 3.1 405B Instruct Meta	36.7	70.3	—	—	96.8	—	—	3	73.8	2024	—	llm	Open weights	405000000000	—	128K	100	0.40	$0.89	$0.89
#170	Devstral 2 Mistral AI	36.7	—	—	—	—	—	—	36.7	—	2025	—	llm	Open weights	—	—	262K	51	0.64	$0.40	$2.00
#171	Granite 3.3 8B IBM	36.6	66.5	—	—	—	—	—	6.7	—	2025	—	llm	—	—	—	—	376	20.60	$0.00	$0.30
#172	Kimi Linear 48B A3B Instruct Moonshot AI	36.3	—	—	—	—	—	—	36.3	—	2025	—	llm	—	—	—	—	—	—	$0.00	$0.00
#173	Llama 3.1 70B Instruct Meta	34.5	64.9	—	—	—	—	—	4	—	2024	—	llm	Open weights	—	2023	131K	1204	0.20	$0.40	$0.40
#174	Devstral Small 2 Mistral AI	34.3	—	—	—	—	—	—	34.3	—	2025	—	llm	—	—	—	—	62	0.75	$0.00	$0.00
#175	Ministral 3 8B Mistral AI	31.7	—	—	—	—	—	—	31.7	—	2025	—	multimodal	Open weights	—	—	262K	86	0.38	$0.15	$0.15

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