#	Model	Score	Price
1	GPT-5.4· OpenAI	57.3	$2.50
2	Gemini 3.1 Pro Preview· Google DeepMind	55.5	$2.00
3	GPT-5.3-Codex· OpenAI	53.1	$1.75
4	GPT-5.4 Mini· OpenAI	51.5	$0.75
5	Claude Sonnet 4.6· Anthropic	50.9	$3.00
6	Claude Opus 4.6 (Fast)· Anthropic	48.1	$30.00
7	U Muse Spark· Unknown	47.5	—
8	GLM 5 Turbo· z-ai	44.2	$1.20
9	GPT-5.4 Nano· OpenAI	43.9	$0.20
10	GLM 5.1· z-ai	43.4	$0.95
11	Qwen3.6 Plus· Alibaba Qwen	42.9	$0.33
12	Gemini 3 Flash Preview· Google DeepMind	42.6	$0.50
13	MiniMax M2.7· minimax	41.9	$0.30
14	MiMo-V2-Pro· xiaomi	41.4	$1.00
15	Qwen3.5 397B A17B· Alibaba Qwen	41.3	$0.39
16	Kimi K2.5· moonshotai	39.5	$0.38
17	Gemini 3 Pro· Google DeepMind	39.4	—
18	Gemma 4 31B (free)· Google DeepMind	38.7	$0.00
19	o3· OpenAI	38.4	$2.00
20	DeepSeek V3.2 Speciale· DeepSeek	37.9	$0.40
21	DeepSeek V3.2· DeepSeek	36.7	$0.26
22	GLM 5V Turbo· z-ai	36.2	$1.20
23	MiMo-V2-Omni· xiaomi	35.5	$0.40
24	Qwen3.5-27B· Alibaba Qwen	34.9	$0.20
25	Qwen3.5-122B-A10B· Alibaba Qwen	34.7	$0.26
26	MiMo-V2-Flash· xiaomi	33.5	$0.09
27	Gemini 2.5 Pro· Google DeepMind	31.9	$1.25
28	Step 3.5 Flash· stepfun	31.6	$0.10
29	Grok 4.1 Fast· xAI	30.9	$0.20
30	Mercury 2· inception	30.6	$0.25
31	Qwen3 Max Thinking· Alibaba Qwen	30.5	$0.78
32	Qwen3.5-35B-A3B· Alibaba Qwen	30.3	$0.16
33	Gemini 3.1 Flash Lite Preview· Google DeepMind	30.1	$0.25
34	gpt-oss-120b (free)· OpenAI	28.6	$0.00
35	Trinity Large Thinking· arcee-ai	27.2	$0.22
36	Qwen3.5-9B· Alibaba Qwen	25.3	$0.05
37	Qwen3 Coder 480B A35B (free)· Alibaba Qwen	24.6	$0.00
38	Mistral Small 4· Mistral AI	24.3	$0.15
39	R1 0528· DeepSeek	24.0	$0.50
40	Grok Code Fast 1· xAI	23.7	$0.20
41	Qwen3 Coder Next· Alibaba Qwen	22.9	$0.15
42	Gemma 4 26B A4B (free)· Google DeepMind	22.4	$0.00
43	Qwen3 Next 80B A3B Instruct (free)· Alibaba Qwen	19.5	$0.00
44	INTELLECT-3· prime-intellect	19.1	$0.20
45	gpt-oss-20b (free)· OpenAI	18.5	$0.00
46	Mistral Medium 3.1· Mistral AI	18.3	$0.40
47	Gemini 2.5 Flash Lite· Google DeepMind	18.1	$0.10
48	Qwen3.5 4B· Alibaba	17.5	—
49	Llama 4 Maverick· Meta	15.6	$0.15
50	Qwen3 Next 80B A3B Instruct· Alibaba Qwen	15.3	$0.09
51	ERNIE 4.5 300B A47B · baidu	14.5	$0.28
52	Solar Pro 3· upstage	13.3	$0.15
53	Llama 3.1 Nemotron Ultra 253B v1· NVIDIA	13.1	$0.60
54	R1 Distill Llama 70B· DeepSeek	11.4	$0.70
55	Phi 4· Microsoft	11.2	$0.07
56	Command A· Cohere	9.9	$2.50
57	Reka Flash 3· rekaai	8.9	$0.10
58	N Nanbeige4.1 3B· Nanbeige	8.9	—
59	NVIDIA Nemotron Nano 9B V2· NVIDIA	8.3	—
60	Llama 4 Scout· Meta	6.7	$0.08
61	Granite 4.0 Micro· ibm-granite	5.0	$0.02
62	LFM2-24B-A2B· liquid	3.6	$0.03
63	Phi 4 Mini Instruct· Microsoft	3.6	—
64	Qwen3.5 2B· Alibaba	3.5	—
65	LFM2.5-1.2B-Thinking (free)· liquid	1.4	$0.00
66	LFM2.5-1.2B-Instruct (free)· liquid	0.8	$0.00

Frequently asked

Pulled from the Artificial Analysis · Coding Index dataset · updated daily

What does Artificial Analysis · Coding Index measure?

Artificial Analysis · Coding Index is a knowledge benchmark in the BenchGecko catalog. 66 AI models have been tested on it. Scores range from 0.8 to 57.3 out of 60.

Which model leads on Artificial Analysis · Coding Index?

GPT-5.4 from OpenAI leads Artificial Analysis · Coding Index with a score of 57.3. The median score across 66 tested models is 29.4.

Is Artificial Analysis · Coding Index saturated?

Yes · the top model on Artificial Analysis · Coding Index has reached 57.3 out of 60, within 5% of the theoretical ceiling. This benchmark is approaching saturation and may be replaced by a harder successor.

Does Artificial Analysis · Coding Index predict performance on other benchmarks?

Yes · Artificial Analysis · Coding Index scores correlate 0.98 with OpenCompass · HLE across 11 shared models. Models that do well on Artificial Analysis · Coding Index tend to do well on OpenCompass · HLE.

How often is Artificial Analysis · Coding Index data refreshed?

BenchGecko pulls updates daily. New model scores on Artificial Analysis · Coding Index appear as soon as they are published by Epoch AI or the model provider.