All Models

Benchmark Rankings

Coding Index

Models ranked by Artificial Analysis Coding Index — measuring code generation, debugging, and programming capability.

97 models ranked · Source: Artificial Analysis

#1
Claude Fable 5 9 providers
76.5 #2
GPT 5.5 30 providers
74.9 #3
Claude Opus 4.8 22 providers
74.3 #4
Claude Opus 4.7 30 providers
73.6 #5
Claude 4.7 Opus 2 providers
73.6 #6
Claude Opus 4.7 (20% off) 1 provider
73.6 #7
GPT-5.4 32 providers
71.1 #8
Gemini 3.5 Flash 15 providers
70.1 #9
Gemini 3.1 Pro Preview 21 providers
68.8 #10
Qwen3.7 Max 16 providers
66 #11
Qwen 3.7 Max 2 providers
66 #12
Kimi K2.7 Code 24 providers
60.8 #13
MiMo V2.5 Pro 15 providers
60.2 #14
DeepSeek V4 Pro 37 providers
59.4 #15
deepseek-ai/DeepSeek-V4-Pro 1 provider
59.4 #16
DeepSeek V4 Pro TEE 1 provider
59.4 #17
MiniMax M3 17 providers
58.6 #18
MiniMax M3 (3x usage) 1 provider
58.6 #19
DeepSeek V4 Flash 32 providers
56.2 #20
GPT 5.4 Nano 22 providers
56.1 #21
GPT 5.4 Mini 25 providers
56.1 #22
Moonshot Kimi K2.6 1 provider
56 #23
Kimi K2.6 47 providers
56 #24
Pro/moonshotai/Kimi-K2.6 1 provider
56 #25
moonshotai/Kimi-K2.6 1 provider
56 #26
Kimi K2.6 TEE 2 providers
56 #27
Qwen3.7 Plus 11 providers
55.9 #28
Qwen 3.7 Plus 3 providers
55.9 #29
GLM-5.1 44 providers
55.8 #30
Pro/zai-org/GLM-5.1 1 provider
55.8 #31
zai-org/GLM-5.1 1 provider
55.8 #32
GLM 5.1 TEE 2 providers
55.8 #33
Qwen3.6 Plus 17 providers
54.5 #34
Qwen 3.6 Plus 3 providers
54.5 #35
Qwen 3.6 27B 2 providers
53.7 #36
Qwen3.6-27B 7 providers
53.7 #37
MiniMax-M2.7 30 providers
52.6 #38
GLM 5.2 30 providers
50.7 #39
Nemotron 3 Ultra 3 providers
49.3 #40
NVIDIA Nemotron 3 Ultra 1 provider
49.3 #41
Nemotron 3 Ultra 550B A55B 4 providers
49.3 #42
Nemotron Ultra 1 provider
49.3 #43
Qwen3.5 397B A17B 19 providers
48.2 #44
Qwen 3.5 397B A17B 2 providers
48.2 #45
Qwen 3.5 397B 1 provider
48.2 #46
Qwen/Qwen3.5-397B-A17B 1 provider
48.2 #47
Qwen3.5 397B A17B TEE 2 providers
48.2 #48
Qwen3.5-97B-A17B 1 provider
48.2 #49
Mistral Medium Latest 3 providers
46.9 #50
Mistral Medium 3.5 4 providers
46.9 #51
Qwen3.5 122B-A10B 11 providers
45.7 #52
Qwen/Qwen3.5-122B-A10B 1 provider
45.7 #53
Qwen3.5 122B A10B TEE 1 provider
45.7 #54
Gemma 4 31B 6 providers
43.4 #55
Ring-2.6-1T 5 providers
42.8 #56
Grok 4.3 15 providers
42.2 #57
o3-mini-high 3 providers
42.1 #58
OpenAI o3-mini (High) 1 provider
42.1 #59
Qwen3.6 35B-A3B 13 providers
41.9 #60
Qwen/Qwen3.6-35B-A3B 1 provider
41.9 #61
o1 12 providers
39.7 #62
OpenAI o1 2 providers
39.7 #63
NVIDIA Nemotron 3 Super 120B A12B 2 providers
37.7 #64
Nemotron 3 Super 120B A12B 3 providers
37.7 #65
Nemotron 3 Super 120B 5 providers
37.7 #66
nemotron-3-super 3 providers
37.7 #67
NVIDIA Nemotron 3 Super 120B 2 providers
37.7 #68
Step 3.7 Flash 4 providers
37.3 #69
Gemini 3.1 Flash Lite Preview 13 providers
34.7 #70
OpenAI o1-preview 2 providers
34 #71
gpt-oss-120b 39 providers
30.4 #72
OpenAI GPT OSS 120B 5 providers
30.4 #73
OpenAI GPT 120B 1 provider
30.4 #74
GPT-OSS 120B TEE 2 providers
30.4 #75
Qwen3.5-9B 10 providers
28.7 #76
Qwen 3.5 9B 1 provider
28.7 #77
Qwen/Qwen3.5-9B 1 provider
28.7 #78
GPT-4o (2024-05-13) 5 providers
24.2 #79
Qwen/Qwen3.5-4B 1 provider
22.6 #80
GPT-4 Turbo 11 providers
21.5 #81
gpt-oss-20b 29 providers
20.7 #82
OpenAI GPT-OSS 20b 2 providers
20.7 #83
GPT-OSS 20B TEE 1 provider
20.7 #84
Mistral Large 3 8 providers
20.1 #85
Claude 3 Opus 3 providers
19.5 #86
Claude Opus 3 2 providers
19.5 #87
Llama-4-Maverick-17B-128E-Instruct-FP8 7 providers
16.3 #88
Llama 4 Maverick 17B Instruct 3 providers
16.3 #89
Llama 4 Maverick 17B 128E Instruct 4 providers
16.3 #90
Meta Llama 4 Maverick 17B 128E 1 provider
16.3 #91
Llama 4 Maverick 3 providers
16.3 #92
Solar Pro 3 3 providers
16.2 #93
GPT-4 8 providers
13.1 #94
Granite 4.1 8B 3 providers
9.5 #95
Llama-4-Scout-17B-16E-Instruct-FP8 2 providers
8.2 #96
Meta Llama 4 Scout 17B 16E 1 provider
8.2 #97
Llama 4 Scout 4 providers
8.2