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
#251	Granite 4.1 8B IBM	10.9	21.8	—	—	—	—	—	—	0	—	—	2026	—	llm	Open weights	—	—	131K	133	0.47	$0.05	$0.10
#252	Sarvam 30B Sarvam	10.8	19.2	—	—	—	—	—	—	2.3	—	—	2026	—	llm	—	—	—	—	214	1.17	$0.00	$0.00
#253	Gemma 3 12B Instruct Google	10.6	17.4	—	—	—	—	—	13.7	0.8	—	—	2025	—	llm	—	—	—	—	—	—	$0.10	$0.30
#254	Nova Lite Amazon	10.5	13.9	—	—	—	—	—	16.7	0.8	—	85.4	2024	—	multimodal	API only	—	—	300K	100	0.50	$0.06	$0.24
#255	Granite 4.0 Micro IBM	10.5	11.9	—	—	—	—	—	18	1.5	—	—	2025	—	llm	Open weights	—	—	131K	—	—	$0.02	$0.11
#256	Tri-21B-Think Trillion Labs	10.1	17.8	—	—	—	—	—	—	2.3	—	—	2026	—	llm	—	—	—	—	—	—	$0.00	$0.00
#257	Jamba Reasoning 3B AI21 Labs	9.2	5.9	—	—	—	—	—	21	0.8	—	—	2025	—	llm	—	—	—	—	—	—	$0.00	$0.00
#258	Llama 3.1 8B Instruct Meta	8.5	13.2	—	—	—	—	—	11.6	0.8	—	72.6	2024	—	llm	Open weights	—	2023	131K	2047	0.20	$0.02	$0.05
#259	Gemma 3n E4B Instruct Google	8.5	8.6	—	—	—	—	—	14.6	2.3	—	—	2025	—	llm	—	—	—	—	56	0.55	$0.00	$0.00
#260	Olmo 3.1 32B Instruct Allen Institute for AI	8.4	16.7	—	—	—	—	—	—	0	—	—	2026	—	llm	—	—	—	—	—	—	$0.00	$0.00
#261	Nova Micro Amazon	8.3	9.4	—	—	—	—	—	14	1.5	—	81.1	2024	—	llm	API only	—	—	128K	100	0.50	$0.03	$0.14
#262	Phi 4 Mini Instruct Microsoft	7.8	10.8	—	—	—	—	—	12.6	0	—	—	2025	—	llm	Open weights	—	—	131K	—	—	$0.08	$0.35
#263	Llama 3.2 11B Instruct Meta	7.7	11.2	—	—	—	—	—	11	0.8	—	—	2024	—	multimodal	Open weights	10600000000	2023	128K	168	0.20	$0.05	$0.05
#264	Granite 3.3 8B IBM	7.6	10.1	—	—	—	—	—	12.7	0	—	—	2025	—	llm	—	—	—	—	376	20.60	$0.00	$0.30
#265	LFM2 8B A1B Liquid AI	7.3	6.8	—	—	—	—	—	15.1	0	—	—	2025	—	llm	—	—	—	—	—	—	$0.00	$0.00
#266	Llama 3 8B Instruct Meta	7.2	11.9	—	—	—	—	—	9.6	0	—	—	2024	—	llm	Open weights	—	2023	8K	81	0.51	$0.04	$0.04
#267	Granite 4.1 3B IBM	7.1	11.9	—	—	—	—	—	—	2.3	—	—	2026	—	llm	—	—	—	—	—	—	$0.00	$0.00
#268	Phi-3 Mini Instruct 3.8B Microsoft	6.9	9	—	—	—	—	—	11.6	0	—	—	2024	—	llm	—	—	—	—	—	—	$0.00	$0.00
#269	Llama 3.2 3B Instruct Meta	6.8	5.2	—	—	—	—	—	8.3	—	—	—	2024	—	llm	Open weights	—	2023	131K	172	0.24	$0.05	$0.34
#270	Molmo2-8B Allen Institute for AI	6.7	13.3	—	—	—	—	—	—	0	—	—	2025	—	llm	—	—	—	—	—	—	$0.00	$0.00
#271	Granite 4.0 H 1B IBM	6.6	8.2	—	—	—	—	—	11.5	0	—	—	2025	—	llm	—	—	—	—	—	—	$0.00	$0.00
#272	Gemma 3 4B Instruct Google	6.4	7.3	—	—	—	—	—	11.2	0.8	—	—	2025	—	llm	—	—	—	—	—	—	$0.00	$0.10
#273	Qwen3.5 2B Alibaba	5.5	7.2	—	—	—	—	—	—	3.8	—	—	2026	—	llm	—	—	—	—	328	0.24	$0.00	$0.10
#274	LFM2-24B-A2B Liquid AI	5.5	10.9	—	—	—	—	—	—	0	—	—	2026	—	llm	Open weights	—	—	128K	208	0.30	$0.03	$0.12
#275	Qwen3 0.6B Alibaba	5.4	4.1	—	—	—	—	—	12.1	0	—	—	2025	—	llm	—	—	—	—	225	0.95	$0.10	$1.30

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