Best open LLMs for coding

Open models ranked by coding, from SWE-bench, LiveCodeBench, Aider and other coding boards. The score shown is the overall llmrun Score; the highlighted column is the coding skill score used for the order.

40 benchmarks4 sourcesUpdated 3 Oct 2026Reference scale 2026-Q4How the score is built

Local models Overall

General Coding Agents Math Science Reasoning

Models ranked by coding llmrun Score
#	Model	llmrun Score	Coding	Agents	Math	Science	Reasoning	Benchmarks	VRAM
1	Kimi K31674 GB · 26 benchmarks		73	61	81	52	63	26	1674 GB
2	GLM 5.3456 GB · 21 benchmarks		67	68	72	49	58	21	456 GB
3	DeepSeek V4 Pro 0813991 GB · 21 benchmarks		63	–	71	46	65	21	991 GB
4	DeepSeek V4 Flash 0731183 GB · 21 benchmarks		59	–	71	45	62	21	183 GB
5	GLM 5.2456 GB · 24 benchmarks		58	60	68	47	52	24	456 GB
6	Kimi K2.6620 GB · 18 benchmarks		57	–	63	43	51	18	620 GB
7	DeepSeek V4.1 Flash458 GB · 10 benchmarks		54	–	76	45	57	10	458 GB
8	MiMo V2.5 Pro615 GB · 6 benchmarks		54	–	–	38	42	6	615 GB
9	Kimi K2.7 Code620 GB · 19 benchmarks		53	46	61	40	50	19	620 GB
10	GLM 5.1457 GB · 13 benchmarks		53	54	57	40	46	13	457 GB
11	GLM 5.3 Flash195 GB · 17 benchmarks		52	63	62	44	37	17	195 GB
12	MiniMax M3257 GB · 19 benchmarks		52	40	46	41	38	19	257 GB
13	Qwen3.8 27B17.4 GB · 9 benchmarks		51	–	57	37	50	9	17.4 GB
14	DeepSeek V4 Pro960 GB · 22 benchmarks		49	–	57	44	49	22	960 GB
15	Kimi K2.5620 GB · 20 benchmarks		49	37	–	40	45	20	620 GB
16	GLM 5457 GB · 15 benchmarks		49	45	–	–	40	15	457 GB
17	MiniMax M2.5138 GB · 11 benchmarks		47	37	–	–	45	11	138 GB
18	DeepSeek V3.1 Terminus415 GB · 5 benchmarks		47	–	–	31	39	5	415 GB
19	Gemma 4 31B IT20.4 GB · 11 benchmarks		47	–	–	32	40	11	20.4 GB
20	DeepSeek R1 0528415 GB · 11 benchmarks		46	–	44	–	32	11	415 GB
21	DeepSeek V3.2 Exp415 GB · 10 benchmarks		46	–	–	30	44	10	415 GB
22	Step 3.7 Flash133 GB · 3 benchmarks	—	46	–	–	30	–	3	133 GB
23	DeepSeek V4 Flash175 GB · 10 benchmarks		46	–	–	36	43	10	175 GB
24	Qwen3.6 35B A3B22.0 GB · 12 benchmarks		44	–	49	35	38	12	22.0 GB
25	Inkling572 GB · 21 benchmarks		43	–	52	40	53	21	572 GB
26	Gemma 4 26B A4B IT16.1 GB · 9 benchmarks		43	–	–	30	33	9	16.1 GB
27	Kimi K2 Thinking620 GB · 9 benchmarks		43	34	–	–	–	9	620 GB
28	MiMo V2.5187 GB · 4 benchmarks		43	–	–	33	–	4	187 GB
29	NVIDIA Nemotron 3 Ultra 550B A55B BF16370 GB · 14 benchmarks		43	–	52	37	46	14	370 GB
30	Qwen3 235B A22B Thinking 2507142 GB · 13 benchmarks		42	–	–	34	37	13	142 GB
31	Qwen3.6 27B17.4 GB · 12 benchmarks		42	–	53	36	37	12	17.4 GB
32	MiniMax M2.7138 GB · 6 benchmarks		41	–	–	35	–	6	138 GB
33	Qwen3 235B A22B Instruct 2507142 GB · 8 benchmarks		41	–	–	–	31	8	142 GB
34	Kimi K2 Instruct620 GB · 10 benchmarks		41	28	–	–	25	10	620 GB
35	GLM 4.7216 GB · 13 benchmarks		41	32	51	36	35	13	216 GB
36	Qwen3 235B A22B142 GB · 10 benchmarks		41	–	–	–	31	10	142 GB
37	GPT OSS 20B12.9 GB · 11 benchmarks		40	–	–	24	26	11	12.9 GB
38	Ring 2.6 1T677 GB · 3 benchmarks	—	40	–	–	33	–	3	677 GB
39	Qwen3 Coder 480B A35B Instruct289 GB · 6 benchmarks	—	40	31	–	–	–	6	289 GB
40	MiMo v2 Flash186 GB · 3 benchmarks	—	40	–	–	17	–	3	186 GB
41	Kimi K2 Instruct 0905620 GB · 6 benchmarks		40	–	–	–	–	6	620 GB
42	DeepSeek R1415 GB · 14 benchmarks		39	–	40	28	29	14	415 GB
43	DeepSeek v3 0324415 GB · 13 benchmarks		39	–	33	27	24	13	415 GB
44	GLM 4.5216 GB · 7 benchmarks		38	32	–	–	–	7	216 GB
45	Qwen3.5 27B17.4 GB · 6 benchmarks		38	–	–	–	41	6	17.4 GB
46	GPT OSS 120B70.5 GB · 20 benchmarks		37	14	–	31	30	20	70.5 GB
47	DeepSeek v3415 GB · 10 benchmarks		37	–	26	22	21	10	415 GB
48	GLM 4.6215 GB · 6 benchmarks		36	31	–	29	–	6	215 GB
49	NVIDIA Nemotron 3 Super 120B A12B BF1674.7 GB · 4 benchmarks		36	–	–	27	–	4	74.7 GB
50	DeepSeek V3.2415 GB · 13 benchmarks		35	36	–	–	43	13	415 GB
51	Qwen3 Coder Next48.2 GB · 3 benchmarks	—	35	–	–	23	–	3	48.2 GB
52	Qwen3 32B20.3 GB · 9 benchmarks		33	–	–	26	26	9	20.3 GB
53	Mistral Large 3 675B Instruct 2512446 GB · 5 benchmarks		33	–	–	26	25	5	446 GB
54	Trinity Large Thinking263 GB · 3 benchmarks	—	32	–	–	26	–	3	263 GB
55	Llama 4 Maverick 17B 128E Instruct265 GB · 17 benchmarks		25	–	29	26	23	17	265 GB
56	Llama 3.3 70B Instruct46.6 GB · 13 benchmarks		22	–	19	17	21	13	46.6 GB
57	Gemma 3 27B IT18.1 GB · 11 benchmarks		18	–	29	16	17	11	18.1 GB
58	Llama 3.1 8B Instruct5.3 GB · 11 benchmarks		14	–	14	7	16	11	5.3 GB

The range after each score is a 90% interval: given the boards a model has results on, its true score is very likely inside it. Short ranges mean many agreeing results; long ranges mean few or conflicting ones.

Why some models are missing. A model gets a score only with results on at least 4 benchmarks across at least 2 categories, one of them reasoning or coding. Skill scores need at least 2 benchmarks in that skill; otherwise they show as –.

VRAM is llmrun's estimate at Q4_K_M (or the smallest quantization we track) for the weights plus a working context. Proprietary models can't run locally, so the VRAM filter hides them.

How the llmrun Score is built · llmrun does not run these benchmarks; scores are aggregated from public sources.