Best Coding AI Models 2026

A definitive ranking of the top coding LLMs and AI models optimized for your specific use cases.

Model	Intelligence	MMLU Pro	Context	GPQA	TTFT (s)	Speed (T/s)	Input Price (1M)	Output Price (1M)
OpenAI: GPT-5.4New OpenAI	51.4	-	1050K	92.0%	120.67	151	$2.50	$15.00
OpenAI: GPT-5.3-CodexNew OpenAI	44.3	-	400K	91.5%	81.50	83	$1.75	$14.00
MoonshotAI: Kimi K2.7 CodeNew Kimi	41.9	-	262K	89.6%	1.21	41	$0.95	$4.00
OpenAI: GPT-5.2-Codex OpenAI	40.1	-	400K	89.9%	1.15	129	$1.75	$14.00
Z.ai: GLM 5New Z AI	39.5	-	203K	82.0%	1.14	46	$1.00	$3.20
OpenAI: GPT-5 Codex OpenAI	36.1	86.5%	400K	83.7%	6.95	162	$1.25	$10.00
Anthropic: Claude Sonnet 4.6New Anthropic	35.9	-	1000K	79.9%	1.05	47	$3.00	$15.00
Kwaipilot: KAT-Coder-Pro V2New KwaiKAT	35.4	-	256K	85.5%	-	-	$0.30	$1.20
OpenAI: GPT-5.1-Codex OpenAI	34.7	86.0%	400K	86.0%	3.56	185	$1.25	$10.00
KAT-Coder-Pro V1 KwaiKAT	34.6	81.3%	-	76.4%	1.10	108	$0.30	$1.20
Z.ai: GLM 4.7 Z AI	33.7	85.6%	203K	85.9%	0.59	116	$0.60	$2.20
OpenAI: GPT-5 OpenAI	31.2	86.0%	400K	80.8%	7.92	85	$1.25	$10.00
OpenAI: GPT-5.1-Codex-Mini OpenAI	30.6	82.0%	400K	81.3%	3.33	212	$0.25	$2.00
StepFun: Step 3.7 FlashNew StepFun	30.3	-	256K	80.9%	0.73	401	$0.20	$1.15
Doubao Seed Code ByteDance Seed	26.0	85.4%	-	76.4%	-	-	$0.00	$0.00
Grok Code Fast 1 SpaceXAI	21.6	79.3%	-	72.7%	-	-	$0.00	$0.00
Qwen: Qwen3 Coder NextNew Alibaba	21.1	-	262K	73.7%	0.89	92	$0.35	$1.20
North Mini CodeNew Cohere	20.6	-	-	75.7%	0.18	86	$0.00	$0.00
Devstral 2 Mistral	19.2	76.2%	-	59.4%	0.69	47	$0.00	$0.00
Qwen3 Coder 480B A35B Instruct Alibaba	18.0	78.8%	-	61.8%	1.68	65	$1.50	$7.50
Devstral Small 2 Mistral	17.4	67.8%	-	53.2%	0.52	58	$0.00	$0.00
Qwen: Qwen3 Next 80B A3B Instruct Alibaba	13.7	81.9%	262K	73.8%	1.12	186	$0.50	$2.00
Qwen: Qwen3 Coder 30B A3B Instruct Alibaba	13.6	70.6%	160K	51.6%	1.50	103	$0.45	$2.25
Devstral Medium Mistral	12.4	70.8%	-	49.2%	-	-	$0.40	$2.00
Devstral Small (May '25) Mistral	11.8	63.2%	-	43.4%	-	-	$0.00	$0.00
Devstral Small (Jul '25) Mistral	9.3	62.2%	-	41.4%	-	-	$0.10	$0.30
Mistral Large 2407 Mistral	7.3	68.3%	131K	47.2%	-	-	$2.00	$6.00
Qwen2.5 Coder 32B Instruct Alibaba	7.1	63.5%	128K	41.7%	-	-	$0.00	$0.00
IBM: Granite 4.1 8BNew IBM	6.7	-	131K	43.3%	0.46	128	$0.05	$0.10
DeepSeek-Coder-V2 DeepSeek	5.1	-	-	-	-	-	$0.00	$0.00
Qwen2.5 Coder Instruct 7B Alibaba	4.5	47.3%	-	33.9%	-	-	$0.00	$0.00
Mistral Large Mistral	4.4	51.5%	128K	35.1%	-	-	$4.00	$12.00
OpenAI: GPT-3.5 Turbo OpenAI	3.6	46.2%	16K	29.7%	0.85	128	$0.50	$1.50
DeepSeek Coder V2 Lite Instruct DeepSeek	3.1	42.9%	-	31.9%	-	-	$0.00	$0.00
NVIDIA: Llama 3.3 Nemotron Super 49B V1.5 NVIDIA	-	-	131K	-	-	-	$0.40	$0.40
Morph: Morph V3 Large Morph	-	-	262K	-	-	-	$0.90	$1.90
Cohere: Command R (08-2024) Cohere	-	-	128K	-	-	-	$0.15	$0.60
OpenAI: GPT-3.5 Turbo (older v0613) OpenAI	-	-	4K	-	-	-	$0.00	$0.00
Qwen: Qwen3 Next 80B A3B Thinking Qwen	-	-	262K	-	-	-	$0.10	$0.78
Morph: Morph V3 Fast Morph	-	-	82K	-	-	-	$0.80	$1.20
OpenAI: GPT-5.1-Codex-Max OpenAI	-	-	400K	-	-	-	$1.25	$10.00
Relace: Relace Search Relace	-	-	256K	-	-	-	$1.00	$3.00
Mistral: Devstral 2 2512 Mistral	-	-	262K	-	-	-	$0.40	$2.00
OpenAI: GPT Audio Mini OpenAI	-	-	128K	-	-	-	$0.60	$2.40
OpenAI: GPT Audio OpenAI	-	-	128K	-	-	-	$2.50	$10.00
Relace: Relace Apply 3 Relace	-	-	256K	-	-	-	$0.85	$1.25
Qwen: Qwen3 Coder 480B A35B Qwen	-	-	1049K	-	-	-	$0.22	$1.80
OpenAI: GPT-5 Image OpenAI	-	-	400K	-	-	-	$10.00	$10.00
Mistral: Codestral 2508 Mistral	-	-	256K	-	-	-	$0.30	$0.90
Pareto Code Router openrouter	-	-	2000K	-	-	-	$-1000000.00	$-1000000.00
Qwen: Qwen3 Coder Plus Qwen	-	-	1000K	-	-	-	$0.65	$3.25
Arcee AI: Coder Large Arcee AI	-	-	33K	-	-	-	$0.50	$0.80
Qwen: Qwen3 Coder Flash Qwen	-	-	1000K	-	-	-	$0.20	$0.97
OpenAI: GPT-5 Pro OpenAI	-	-	400K	-	-	-	$15.00	$120.00