What is the cheapest AI model for chat?

The cheapest AI chat models are typically smaller models like GPT-3.5-turbo, Claude Instant, or open-source models on platforms like Together AI and Groq. Prices can be as low as $0.10-0.25 per million tokens. However, cheaper models may have reduced capabilities compared to flagship models like GPT-4 or Claude 3 Opus. Use CloudPrice to compare current prices across all providers.

How much does GPT-4 cost?

GPT-4 pricing varies by version. GPT-4 Turbo costs approximately $10 per million input tokens and $30 per million output tokens. GPT-4o is more affordable at around $5/$15 per million tokens. OpenAI also offers GPT-4o-mini at significantly lower prices. Pricing may change, so check CloudPrice for current rates.

What is the difference between input and output tokens?

Input tokens are the text you send to the AI model (your prompts, context, and conversation history). Output tokens are what the model generates in response. Most AI providers charge differently for input and output tokens, with output tokens typically being 2-4x more expensive because they require more computation to generate.

Which AI model has the largest context window?

Google's Gemini 1.5 Pro currently offers one of the largest context windows at 1 million tokens. Anthropic's Claude 3 models support 200K tokens, while OpenAI's GPT-4 Turbo supports 128K tokens. Larger context windows allow processing more text in a single request but may cost more.

What does 'supports vision' mean for AI models?

AI models with vision support can process and understand images in addition to text. You can send images as part of your prompt and the model can describe, analyze, or answer questions about them. Examples include GPT-4 Vision, Claude 3, and Gemini Pro Vision. Vision capabilities typically cost extra per image processed.

AI Models Pricing & Benchmarks Comparison - 1900+ LLM Models

Compare AI model pricing and benchmarks across providers including OpenAI, Anthropic, Google, Amazon Bedrock, Azure, Mistral, and more. Filter by model capabilities like vision, function calling, and reasoning support. Find the most cost-effective model for your use case. Currently tracking 2,529 models across 98 providers. Last update: April 17, 2026 at 12:00 AM UTC

Model	Creator	Input Price, $	Output Price, $	Inference Providers	Context	Max Output	Intelligence	Coding
Kimi K2 Thinking	Moonshot AI (Kimi)	0.574	1.20	compare (9)	262K	33K	40.9#1	34.8#1
MiniMax M2.1	MiniMax	0.290	0.950	compare (7)	1.0M	131K	39.4#2	32.8#2
Kimi K2.5	Moonshot AI (Kimi)	0.383	1.72	compare (8)	262K	98K	37.3#3	25.8#9
MiniMax M2	MiniMax	0.255	1.00	compare (7)	205K	131K	36.1#4	29.2#6
GLM-4.7	Zhipu AI	0.390	1.75	compare (10)	205K	131K	34.2#5	32.0#3
DeepSeek V3.1 Terminus	DeepSeek	0.210	0.790	compare (5)	164K	66K	28.5#6	31.9#4
DeepSeek V3.2	DeepSeek	0.260	0.380	compare (11)	164K	66K	28.4#7	30.0#5
DeepSeek V3.1	DeepSeek	0.150	0.750	compare (10)	164K	66K	27.7#8	28.4#7
GLM-4.5	Zhipu AI	0.400	1.60	compare (6)	131K	98K	26.4#9	26.3#8
Qwen3 Coder 480B A35B Instruct	Alibaba	0.220	1.30	compare (6)	262K	66K	24.8#10	24.6#10
GPT OSS 120B	OpenAI	0.039	0.190	compare (17)	131K	131K	24.5#11	15.5#20
MiniMax M1 80K	MiniMax	0.100	0.100	compare (2)	1.0M	40K	24.4#12	14.5#23
GLM-4.6	Zhipu AI	0.390	1.90	compare (8)	205K	131K	23.4#13	19.7#14
GLM-4.5 Air	Zhipu AI	0.130	0.850	compare (5)	131K	98K	23.2#14	23.8#11
Mistral Large 3	Mistral AI	0.500	1.20	compare (4)	262K	8K	22.8#15	22.7#12
DeepSeek V3 0324	DeepSeek	0.200	0.600	compare (9)	164K	16K	22.3#16	22.0#13
Qwen3 VL 235B A22B Instruct	Alibaba	0.200	0.880	compare (4)	262K	33K	20.8#17	16.5#17
GPT OSS 20B	OpenAI	0.030	0.140	compare (13)	131K	131K	20.8#18	14.4#24
Qwen3 Next 80B A3B Instruct	Alibaba	0.090	0.900	compare (7)	262K	66K	20.1#19	15.3#21
Qwen3 Coder 30B A3B Instruct	Alibaba	0.070	0.270	compare (4)	262K	66K	20.0#20	19.4#15
Qwen3 235B A22B	Alibaba	0.180	0.540	compare (8)	262K	131K	19.8#21	17.4#16
QwQ 32B	Alibaba	0.150	0.200	compare (8)	131K	16K	19.7#22	N/A
Devstral Small 1.0	Mistral AI	0.100	0.300	compare (2)	131K	N/A	18.0#23	12.2#29
Llama 3.1 405B Instruct	Meta	0.120	0.300	compare (11)	131K	16K	17.4#24	14.5#22
Qwen3 VL 32B Instruct	Alibaba	0.104	0.416	compare (3)	131K	33K	17.2#25	15.6#19
DeepSeek R1 Distill Qwen 32B	DeepSeek	0.270	0.270	compare (6)	131K	32K	17.2#26	N/A
Qwen3 235B A22B Instruct	Alibaba	0.090	0.580	compare (7)	262K	33K	17.0#27	14.0#26
DeepSeek V3	DeepSeek	0.200	0.200	compare (12)	164K	82K	16.5#28	16.4#18
DeepSeek R1	DeepSeek	0.280	0.420	compare (14)	164K	66K	16.4#29	7.8#40
Qwen3 VL 30B A3B Instruct	Alibaba	0.130	0.520	compare (4)	262K	33K	16.1#30	14.3#25
DeepSeek R1 Distill Llama 70B	DeepSeek	0.200	0.600	compare (10)	131K	16K	16.0#31	11.4#31
DeepSeek R1 Distill Qwen 14B	DeepSeek	0.070	0.070	compare (4)	131K	16K	15.8#32	N/A
Qwen2.5 72B Instruct	Alibaba	0.120	0.300	compare (7)	131K	16K	15.6#33	11.9#30
QwQ 32B Preview	Alibaba	0.287	0.861	compare (2)	33K	16K	15.2#34	N/A
Qwen3 30B A3B	Alibaba	0.080	0.280	compare (5)	131K	16K	15.0#35	11.0#32
Qwen3 32B	Alibaba	0.080	0.240	compare (11)	131K	16K	14.5#36	13.8#27
Llama 3.3 70B Instruct	Meta	0.100	0.300	compare (16)	131K	120K	14.5#37	10.7#37
Qwen3 VL 8B Instruct	Alibaba	0.080	0.200	compare (4)	131K	33K	14.3#38	7.3#42
Qwen3 4B	Alibaba	0.080	0.200	compare (3)	131K	8K	14.2#39	9.5#38
NVIDIA Llama 3.1 Nemotron 70B Instruct	NVIDIA	0.120	0.300	compare (3)	131K	16K	13.4#40	10.8#35
Qwen2.5 32B Instruct	Alibaba	0.060	0.200	compare (3)	131K	8K	13.2#41	N/A
Nemotron Nano 2 9B	NVIDIA	0.040	0.160	compare (5)	131K	8K	13.2#42	7.5#41
Qwen2.5 Coder 32B Instruct	Alibaba	0.050	0.100	compare (7)	131K	8K	12.9#43	N/A
Qwen3 14B	Alibaba	0.060	0.200	compare (6)	131K	16K	12.8#44	12.4#28
GLM-4.5 V	Zhipu AI	0.600	1.20	compare (5)	131K	32K	12.7#45	10.8#36
Qwen3 4B Instruct	Alibaba	0.200	0.200	compare (1)	262K	33K	12.5#47	9.1#39
Qwen3 30B A3B Instruct	Alibaba	0.090	0.300	compare (3)	262K	33K	12.5#46	11.0#33
Llama 3.1 70B Instruct	Meta	0.120	0.300	compare (12)	131K	8K	12.5#48	10.9#34
DeepSeek V2.5	DeepSeek	1.20	1.20	compare (1)	33K	N/A	12.3#49	N/A
DeepSeek R1 Distill Llama 8B	DeepSeek	0.050	0.050	compare (2)	131K	16K	12.1#50	N/A
Llama 3.1 8B Instruct	Meta	0.020	0.040	compare (15)	200K	128K	11.8#51	4.9#46
Qwen2 72B Instruct	Alibaba	0.900	0.900	compare (1)	33K	N/A	11.7#52	N/A
Qwen3 8B	Alibaba	0.050	0.200	compare (3)	131K	8K	10.6#53	7.1#43
Nemotron Nano 2 12B VL	NVIDIA	0.100	0.100	compare (3)	131K	4K	10.1#54	5.9#45
Qwen2.5 Coder 7B Instruct	Alibaba	0.010	0.030	compare (3)	131K	8K	10.0#55	N/A
Mixtral 8x22B Instruct	Mistral AI	1.20	1.20	compare (4)	66K	2K	9.8#56	N/A
Llama 3.2 3B Instruct	Meta	0.015	0.020	compare (9)	131K	32K	9.7#58	N/A
Llama 2 7B Chat	Meta	0.050	0.200	compare (3)	4K	4K	9.7#57	N/A
DeepSeek R1 Distill Qwen 1.5B	DeepSeek	0.100	0.100	compare (2)	131K	N/A	9.1#59	N/A
Llama 3 70B Instruct	Meta	0.120	0.300	compare (7)	131K	8K	8.9#60	6.8#44
Llama 2 70B Chat	Meta	0.500	0.900	compare (6)	4K	4K	8.4#62	N/A
Llama 2 13B Chat	Meta	0.100	0.200	compare (3)	4K	4K	8.4#61	N/A
Mixtral 8x7B Instruct	Mistral AI	0.070	0.280	compare (9)	33K	16K	7.7#63	N/A
Mistral 7B Instruct	Mistral AI	0.010	0.100	compare (8)	127K	16K	7.4#64	N/A
Qwen3 1.7B	Alibaba	0.100	0.100	compare (2)	131K	8K	6.8#65	1.4#48
Llama 3 8B Instruct	Meta	0.030	0.040	compare (7)	32K	8K	6.4#66	4.0#47
Llama 3.2 1B Instruct	Meta	0.027	0.080	compare (5)	128K	16K	6.3#67	0.6#50
Qwen3 0.6B	Alibaba	0.100	0.100	compare (2)	41K	8K	5.7#68	0.9#49
Capybara 1.9 7B	Nous Research	0.200	0.200	compare (1)	33K	N/A	N/A	N/A
Chronos Hermes 2 13B	Nous Research	0.200	0.200	compare (1)	4K	4K	N/A	N/A
Code Llama 13B	Meta	0.200	0.200	compare (1)	16K	16K	N/A	N/A
Code Llama 13B Instruct	Meta	0.200	0.200	compare (1)	16K	16K	N/A	N/A
Code Llama 13B Python	Meta	0.200	0.200	compare (1)	16K	16K	N/A	N/A
Code Llama 34B	Meta	0.900	0.900	compare (1)	16K	16K	N/A	N/A
Code Llama 34B Instruct	Meta	0.350	0.900	compare (2)	16K	16K	N/A	N/A
Code Llama 34B Python	Meta	0.900	0.900	compare (1)	16K	16K	N/A	N/A
Code Llama 70B	Meta	0.900	0.900	compare (1)	4K	4K	N/A	N/A
Code Llama 70B Instruct	Meta	0.700	0.900	compare (2)	16K	16K	N/A	N/A
Code Llama 70B Python	Meta	0.900	0.900	compare (1)	4K	4K	N/A	N/A
Code Llama 7B	Meta	0.200	0.200	compare (1)	16K	16K	N/A	N/A
Code Llama 7B Instruct	Meta	0.200	0.200	compare (2)	16K	16K	N/A	N/A
Code Llama 7B Python	Meta	0.200	0.200	compare (1)	16K	16K	N/A	N/A
CodeGemma 2B	Google	0.100	0.100	compare (1)	8K	8K	N/A	N/A
CodeGemma 7B	Google	0.200	0.200	compare (1)	8K	8K	N/A	N/A
Cogito 2 671B	DeepCogito	1.20	1.20	compare (1)	164K	N/A	N/A	N/A
Cogito Llama 1 1.3B Preview	DeepCogito	0.100	0.100	compare (1)	131K	N/A	N/A	N/A
Cogito Llama 1 1.8B Preview	DeepCogito	0.200	0.200	compare (1)	131K	N/A	N/A	N/A
Cogito Llama 1 70B Preview	DeepCogito	0.900	0.900	compare (1)	131K	N/A	N/A	N/A
Cogito Qwen 1 14B Preview	DeepCogito	0.200	0.200	compare (1)	131K	N/A	N/A	N/A
Cogito Qwen 1 32B Preview	DeepCogito	0.900	0.900	compare (1)	131K	N/A	N/A	N/A
DBRX Instruct	Databricks	1.20	1.20	compare (1)	33K	N/A	N/A	N/A
DeepSeek Coder 1.3B Base	DeepSeek	0.100	0.100	compare (1)	16K	16K	N/A	N/A
DeepSeek Coder 33B Instruct	DeepSeek	0.900	0.900	compare (1)	16K	16K	N/A	N/A
DeepSeek Coder 7B Base	DeepSeek	0.200	0.200	compare (1)	4K	4K	N/A	N/A
DeepSeek Coder 7B Base V1.5	DeepSeek	0.200	0.200	compare (1)	4K	4K	N/A	N/A
DeepSeek Coder 7B Instruct V1.5	DeepSeek	0.200	0.200	compare (1)	4K	4K	N/A	N/A
DeepSeek Coder V2 Instruct	DeepSeek	1.20	1.20	compare (1)	66K	8K	N/A	N/A
DeepSeek Coder V2 Lite Base	DeepSeek	0.500	0.500	compare (1)	164K	8K	N/A	N/A
DeepSeek Coder V2 Lite Instruct	DeepSeek	0.500	0.500	compare (1)	164K	8K	N/A	N/A
DeepSeek Prover V2	DeepSeek	1.20	1.20	compare (1)	164K	N/A	N/A	N/A
DeepSeek R1 0528	DeepSeek	0.200	0.600	compare (8)	164K	33K	N/A	N/A
DeepSeek R1 0528 Distill Qwen3 8B	DeepSeek	0.200	0.200	compare (1)	131K	N/A	N/A	N/A
DeepSeek R1 Basic	DeepSeek	0.550	2.19	compare (1)	128K	20K	N/A	N/A
DeepSeek R1 Distill Qwen 7B	DeepSeek	0.072	0.144	compare (3)	131K	16K	N/A	N/A
DeepSeek V2 Lite Chat	DeepSeek	0.500	0.500	compare (1)	164K	N/A	N/A	N/A
ERNIE 4.5 21B A3B PT	Baidu	0.100	0.100	compare (1)	4K	4K	N/A	N/A
ERNIE 4.5 300B A47B PT	Baidu	0.100	0.100	compare (1)	4K	4K	N/A	N/A
FLUX.1 Dev	Black Forest Labs	0.100	0.100	compare (1)	4K	4K	N/A	N/A
FLUX.1 Dev ControlNet Union	Black Forest Labs	0.0010	0.0010	compare (1)	4K	4K	N/A	N/A
FLUX.1 Schnell	Black Forest Labs	0.100	0.100	compare (1)	4K	4K	N/A	N/A
Gemma 2B IT	Google	0.100	0.100	compare (1)	8K	8K	N/A	N/A
Gemma 3 27B IT	Google	0.060	0.160	compare (6)	131K	16K	N/A	N/A
Gemma 7B	Google	0.200	0.200	compare (2)	8K	8K	N/A	N/A
Gemma 7B Instruct	Google	0.050	0.080	compare (2)	8K	8K	N/A	N/A
Gemma2 9B IT	Google	0.200	0.200	compare (2)	8K	8K	N/A	N/A
GPT OSS 120B Safeguard	OpenAI	0.150	0.600	compare (2)	131K	66K	N/A	N/A
GPT OSS 20B Safeguard	OpenAI	0.070	0.200	compare (5)	131K	66K	N/A	N/A
GTE Base	Alibaba	0.0080	N/A	compare (1)	512	N/A	N/A	N/A
GTE Large	Alibaba	0.016	N/A	compare (1)	512	N/A	N/A	N/A
Hermes 2 Mixtral 8x7B DPO	Nous Research	0.500	0.500	compare (1)	33K	N/A	N/A	N/A
Hermes 2 Yi 34B	Nous Research	0.900	0.900	compare (1)	4K	4K	N/A	N/A
Hermes Llama2 13B	Nous Research	0.200	0.200	compare (1)	4K	4K	N/A	N/A
Hermes Llama2 70B	Nous Research	0.900	0.900	compare (1)	4K	4K	N/A	N/A
Hermes Llama2 7B	Nous Research	0.200	0.200	compare (1)	4K	4K	N/A	N/A
InternVL3 38B	Opengvlab	0.900	0.900	compare (1)	16K	16K	N/A	N/A
InternVL3 78B	Opengvlab	0.900	0.900	compare (1)	16K	16K	N/A	N/A
InternVL3 8B	Opengvlab	0.200	0.200	compare (1)	16K	16K	N/A	N/A
Kimi K2 Instruct	Moonshot AI (Kimi)	0.500	2.00	compare (6)	262K	33K	N/A	N/A
KwaiPilot KAT 32B Dev	KwaiPilot	0.900	0.900	compare (1)	131K	N/A	N/A	N/A
KwaiPilot KAT 72B Dev Exp	KwaiPilot	0.900	0.900	compare (1)	131K	N/A	N/A	N/A
KwaiPilot KAT Coder	KwaiPilot	0.900	0.900	compare (1)	262K	N/A	N/A	N/A
Llama 2 13B	Meta	0.100	0.200	compare (2)	4K	4K	N/A	N/A
Llama 2 70B	Meta	0.100	0.100	compare (2)	4K	4K	N/A	N/A
Llama 2 7B	Meta	0.050	0.200	compare (2)	4K	4K	N/A	N/A
Llama 3 8B	Meta	0.050	0.080	compare (4)	8K	8K	N/A	N/A
Llama 3.1 405B Instruct Long	Meta	0.100	0.100	compare (1)	4K	4K	N/A	N/A
Llama 3.1 8B	Meta	0.100	0.100	compare (4)	131K	8K	N/A	N/A
Llama 3.2 11B Vision Instruct	Meta	0.015	0.025	compare (7)	131K	16K	N/A	N/A
Llama 3.2 1B	Meta	0.100	0.100	compare (3)	131K	8K	N/A	N/A
Llama 3.2 3B	Meta	0.100	0.100	compare (3)	131K	8K	N/A	N/A
Llama 3.2 90B Vision Instruct	Meta	0.900	0.900	compare (4)	128K	16K	N/A	N/A
Llama 3.3 70B Instruct	Meta	0.720	0.720	compare (4)	131K	8K	N/A	N/A
Llama Guard 2 8B	Meta	0.200	0.200	compare (1)	8K	8K	N/A	N/A
Llama Guard 3 1B	Meta	0.100	0.100	compare (1)	131K	N/A	N/A	N/A
Llama Guard 3 8B	Meta	0.020	0.030	compare (5)	131K	16K	N/A	N/A
Llama Guard 7B	Meta	0.200	0.200	compare (1)	4K	4K	N/A	N/A
Llama4 Maverick Instruct Basic	Meta	0.220	0.880	compare (1)	131K	N/A	N/A	N/A
Llama4 Scout Instruct Basic	Meta	0.150	0.600	compare (1)	131K	N/A	N/A	N/A
LLaVA Yi 34B	01.AI	0.900	0.900	compare (1)	4K	4K	N/A	N/A
Ministral 3 14B Instruct	Mistral AI	0.200	0.200	compare (2)	256K	8K	N/A	N/A
Ministral 3 3B Instruct	Mistral AI	0.100	0.100	compare (2)	256K	8K	N/A	N/A
Ministral 3 8B Instruct	Mistral AI	0.150	0.150	compare (2)	256K	8K	N/A	N/A
Mistral 3 7B Instruct	Mistral AI	0.200	0.200	compare (1)	33K	N/A	N/A	N/A
Mistral 7B	Mistral AI	0.050	0.200	compare (4)	33K	8K	N/A	N/A
Mistral 7B Instruct 4K	Mistral AI	0.200	0.200	compare (1)	33K	N/A	N/A	N/A
Mistral Small 24B Instruct	Mistral AI	0.050	0.080	compare (3)	33K	16K	N/A	N/A
Mixtral 8x22B	Mistral AI	1.20	1.20	compare (2)	66K	8K	N/A	N/A
Mixtral 8x7B	Mistral AI	0.460	0.500	compare (3)	33K	8K	N/A	N/A
MythoMax L2 13B	Gryphe	0.060	0.060	compare (4)	4K	4K	N/A	N/A
Nemo Base	Mistral AI	0.200	0.200	compare (1)	128K	N/A	N/A	N/A
Nemo Instruct	Mistral AI	0.020	0.040	compare (5)	131K	N/A	N/A	N/A
Nemotron Nano 2 12B	NVIDIA	0.200	0.200	compare (2)	131K	8K	N/A	N/A
Nomic Embed Text 1	Nomic AI	0.0080	N/A	compare (1)	8K	N/A	N/A	N/A
Nomic Embed Text 1.5	Nomic AI	0.0080	N/A	compare (1)	8K	N/A	N/A	N/A
OpenChat 3.5 106 7B	OpenChat	0.200	0.200	compare (1)	8K	8K	N/A	N/A
OpenOrca 7B	Openorca	0.200	0.200	compare (1)	33K	N/A	N/A	N/A
Phi-2 3B	Microsoft	0.100	0.100	compare (1)	2K	2K	N/A	N/A
Phi-3 Mini Instruct	Microsoft	0.100	0.100	compare (2)	131K	4K	N/A	N/A
Phi-3 Vision 128K Instruct	Microsoft	0.200	0.200	compare (1)	32K	N/A	N/A	N/A
Phind Code Llama 1 34B	Phind	0.900	0.900	compare (1)	16K	16K	N/A	N/A
Phind Code Llama 1 34B Python	Phind	0.900	0.900	compare (1)	16K	16K	N/A	N/A
Phind Code Llama 2 34B	Phind	0.900	0.900	compare (1)	16K	16K	N/A	N/A
Pythia 12B	EleutherAI	0.200	0.200	compare (1)	2K	2K	N/A	N/A
Qwen1.5 72B Chat	Alibaba	0.900	0.900	compare (1)	33K	N/A	N/A	N/A
Qwen1.5 7B Code	Alibaba	0.200	0.200	compare (1)	66K	N/A	N/A	N/A
Qwen2 72B	Alibaba	0.900	0.900	compare (1)	131K	N/A	N/A	N/A
Qwen2 7B Instruct	Alibaba	0.200	0.200	compare (1)	33K	N/A	N/A	N/A
Qwen2 VL 2B Instruct	Alibaba	0.100	0.100	compare (1)	33K	N/A	N/A	N/A
Qwen2 VL 72B Instruct	Alibaba	0.130	0.400	compare (3)	131K	2K	N/A	N/A
Qwen2 VL 7B Instruct	Alibaba	0.020	0.060	compare (2)	131K	N/A	N/A	N/A
Qwen2.5 0.5B Instruct	Alibaba	0.100	0.100	compare (1)	33K	N/A	N/A	N/A
Qwen2.5 1.5B Instruct	Alibaba	0.100	0.100	compare (1)	33K	N/A	N/A	N/A
Qwen2.5 14B	Alibaba	0.200	0.200	compare (1)	131K	N/A	N/A	N/A
Qwen2.5 14B Instruct	Alibaba	0.200	0.200	compare (2)	131K	8K	N/A	N/A
Qwen2.5 32B	Alibaba	0.900	0.900	compare (1)	131K	N/A	N/A	N/A
Qwen2.5 72B	Alibaba	0.900	0.900	compare (1)	131K	N/A	N/A	N/A
Qwen2.5 7B	Alibaba	0.200	0.200	compare (1)	131K	N/A	N/A	N/A
Qwen2.5 7B Instruct	Alibaba	0.040	0.070	compare (6)	131K	8K	N/A	N/A
Qwen2.5 Coder 0.5B	Alibaba	0.100	0.100	compare (1)	33K	N/A	N/A	N/A
Qwen2.5 Coder 0.5B Instruct	Alibaba	0.100	0.100	compare (1)	33K	N/A	N/A	N/A
Qwen2.5 Coder 1.5B	Alibaba	0.100	0.100	compare (1)	33K	N/A	N/A	N/A
Qwen2.5 Coder 1.5B Instruct	Alibaba	0.100	0.100	compare (1)	33K	N/A	N/A	N/A
Qwen2.5 Coder 14B	Alibaba	0.200	0.200	compare (1)	33K	N/A	N/A	N/A
Qwen2.5 Coder 14B Instruct	Alibaba	0.200	0.200	compare (2)	131K	8K	N/A	N/A
Qwen2.5 Coder 32B	Alibaba	0.900	0.900	compare (1)	33K	N/A	N/A	N/A
Qwen2.5 Coder 3B	Alibaba	0.100	0.100	compare (1)	33K	N/A	N/A	N/A
Qwen2.5 Coder 3B Instruct	Alibaba	0.010	0.030	compare (2)	33K	N/A	N/A	N/A
Qwen2.5 Coder 7B	Alibaba	0.010	0.030	compare (2)	33K	8K	N/A	N/A
Qwen2.5 Math 72B Instruct	Alibaba	0.574	0.900	compare (2)	4K	4K	N/A	N/A
Qwen2.5 VL 32B Instruct	Alibaba	0.200	0.600	compare (4)	131K	8K	N/A	N/A
Qwen2.5 VL 3B Instruct	Alibaba	0.200	0.200	compare (2)	131K	8K	N/A	N/A
Qwen2.5 VL 72B Instruct	Alibaba	0.130	0.400	compare (6)	131K	8K	N/A	N/A
Qwen2.5 VL 7B Instruct	Alibaba	0.200	0.200	compare (2)	131K	8K	N/A	N/A
Qwen3 1.7B FP8 Draft	Alibaba	0.100	0.100	compare (1)	262K	N/A	N/A	N/A
Qwen3 235B A22B Thinking	Alibaba	0.149	0.880	compare (7)	262K	33K	N/A	N/A
Qwen3 30B A3B Thinking	Alibaba	0.080	0.400	compare (3)	262K	33K	N/A	N/A
Qwen3 Coder 480B Instruct	Alibaba	0.900	0.900	compare (1)	4K	4K	N/A	N/A
Qwen3 Next 80B A3B Thinking	Alibaba	0.098	0.780	compare (7)	262K	66K	N/A	N/A
Qwen3 VL 235B A22B Thinking	Alibaba	0.220	0.880	compare (4)	262K	33K	N/A	N/A
Qwen3 VL 30B A3B Thinking	Alibaba	0.130	0.600	compare (4)	262K	33K	N/A	N/A
RolmOCR	IBM	0.200	0.200	compare (1)	128K	N/A	N/A	N/A
Snorkel Mistral PairRM DPO	Snorkel AI	0.200	0.200	compare (1)	33K	N/A	N/A	N/A
StableCode 3B	Stability AI	0.100	0.100	compare (1)	4K	4K	N/A	N/A
StarCoder 16B	Hugging Face	0.200	0.200	compare (1)	8K	8K	N/A	N/A
StarCoder 7B	Hugging Face	0.200	0.200	compare (1)	8K	8K	N/A	N/A
StarCoder2 15B	Hugging Face	0.200	0.200	compare (1)	16K	16K	N/A	N/A
StarCoder2 3B	Hugging Face	0.100	0.100	compare (1)	16K	16K	N/A	N/A
StarCoder2 7B	Hugging Face	0.200	0.200	compare (1)	16K	16K	N/A	N/A
UAE 1 Large	Whereisai	0.016	N/A	compare (1)	512	N/A	N/A	N/A
Yi 34B	01.AI	0.900	0.900	compare (1)	4K	4K	N/A	N/A
Yi 34B Capybara	01.AI	0.900	0.900	compare (1)	200K	N/A	N/A	N/A
Yi 34B Chat	01.AI	0.900	0.900	compare (1)	4K	4K	N/A	N/A
Yi 6B	01.AI	0.200	0.200	compare (1)	4K	4K	N/A	N/A
Yi Large	01.AI	3.00	3.00	compare (1)	33K	N/A	N/A	N/A
Zephyr 7B Beta	Hugging Face	0.200	0.200	compare (1)	33K	16K	N/A	N/A

AI Model Comparison