Benchmarks / Artificial Analysis

Reported by Artificial Analysis

Artificial Analysis

Artificial Analysis's blend of its coding evaluations.

Last updated 9 Nov 2026

Results dated
20 Oct 2026
Results
187 configurations of 130 models
Unit
index score
Licence
Artificial Analysis commercial data licence

Artificial Analysis in brief

What it measures. Artificial Analysis is a third-party benchmark, shown here with credit. Measured here: Artificial Analysis's blend of its coding evaluations.

Latest results. , 130 models ranked.

Top 3 on Artificial Analysis Coding Index (index score, higher is better, each model at its best setting):

  1. Claude Fable 5.1 (max reasoning) (Anthropic): 81.6
  2. GPT-5.6 Sol (extra-high reasoning) (OpenAI): 78.3
  3. Claude Opus 5 (max reasoning) (Anthropic): 78.0

How to cite. Artificial Analysis, via Spring Prompt, results dated 20 October 2026. https://springprompt.com/benchmarks/artificial-analysis These results belong to Artificial Analysis, not to us. Licence: Artificial Analysis commercial data licence. Credit Artificial Analysis first.

Artificial Analysis Coding Index: Qwen3.6-27B

Top 15 of 130 results · index score, higher is better. Choose a model to highlight it.Clear highlight

  1. 1 Claude Fable 5.1 (max reasoning)Anthropic 81.6
  2. 2 GPT-5.6 Sol (extra-high reasoning)OpenAI 78.3
  3. 3 Claude Opus 5 (max reasoning)Anthropic 78.0
  4. 4 GPT-6 Astra (high reasoning)OpenAI 77.1
  5. 5 Grok 4.6 (high reasoning)xAI 76.8
  6. 6 GPT-5.6 Terra (max reasoning)OpenAI 76.7
  7. 7 Claude Fable 5 (max reasoning)Anthropic 76.5
  8. 7 Muse Spark 1.3 (extra-high reasoning)Meta 76.5
  9. 9 Gemini 3.8 Flash (high reasoning)Google 76.3
  10. 10 Qwen3.8-Max (0902)Alibaba 76.2
  11. 10 Kimi K3 (max reasoning)Moonshot AI 76.2
  12. 12 Gemini 3.7 Flash (high reasoning)Google 76.1
  13. 13 GPT-5.5 (extra-high reasoning)OpenAI 74.9
  14. 14 GLM-5.3 (max reasoning)Z.ai 74.8
  15. 15 Claude Opus 4.8 (max reasoning)Anthropic 74.3
  16. 51 Qwen3.6-27BAlibaba 53.7

Full results

Artificial Analysis: Artificial Analysis Coding Index, index score, higher is better
#ModelArtificial Analysis Coding Index
index score, higher is better
Price
$ per million tokens, in / out
1 Claude Fable 5.1 (max reasoning)Anthropic · best of 5 settings
81.6
$10 / $50
2 GPT-5.6 Sol (extra-high reasoning)OpenAI · best of 6 settings
78.3
$4 / $20
3 Claude Opus 5 (max reasoning)Anthropic · best of 5 settings
78.0
$5 / $25
4 GPT-6 Astra (high reasoning)OpenAI · best of 5 settings
77.1
$10 / $50
5 Grok 4.6 (high reasoning)xAI · best of 4 settings
76.8
$2 / $6
6 GPT-5.6 Terra (max reasoning)OpenAI · best of 6 settings
76.7
$2 / $12
7 Claude Fable 5 (max reasoning)Anthropic
76.5
$10 / $50
7 Muse Spark 1.3 (extra-high reasoning)Meta · best of 2 settings
76.5
$1.25 / $4.25
9 Gemini 3.8 Flash (high reasoning)Google · best of 3 settings
76.3
$1.50 / $7.50
10 Qwen3.8-Max (0902)Alibaba
76.2
$2 / $6
10 Kimi K3 (max reasoning)Moonshot AI · best of 2 settings
76.2
$3 / $15
12 Gemini 3.7 Flash (high reasoning)Google · best of 3 settings
76.1
$1.50 / $7.50
13 GPT-5.5 (extra-high reasoning)OpenAI · best of 5 settings
74.9
$5 / $30
14 GLM-5.3 (max reasoning)Z.ai
74.8
$1.40 / $4.40
15 Claude Opus 4.8 (max reasoning)Anthropic
74.3
$5 / $25
16 Claude Opus 4.7 (max reasoning)Anthropic
73.6
$5 / $25
17 Qwen3.8-Flash-NextAlibaba
73.1
–
18 Grok 4.5 (high reasoning)xAI
72.4
$2 / $6
19 Muse Spark 1.2 (extra-high reasoning)Meta
72.2
$1.25 / $4.25
20 Qwen3.8-2.4T-A95BAlibaba
71.9
$2 / $6
21 Qwen3.8-Max (0803)Alibaba
71.8
–
22 Claude Sonnet 5 (max reasoning)Anthropic · best of 2 settings
71.5
$2 / $10
22 GLM-5.3-FlashZ.ai
71.5
$0.15 / $0.50
24 GPT-5.6 Luna (max reasoning)OpenAI · best of 6 settings
71.4
$0.20 / $1.20
25 Muse Spark 1.1 (extra-high reasoning)Meta
71.3
$1.25 / $4.25
26 GPT-5.4 (extra-high reasoning)OpenAI
71.1
$2.50 / $15
27 Gemini 3.5 Flash (high reasoning)Google
70.1
$1.50 / $9
28 Gemini 3.6 Flash (high reasoning)Google
69.2
$1.50 / $7.50
29 DeepSeek-V4-Flash (0731, max reasoning)DeepSeek
69.1
$0.13 / $0.40
30 DeepSeek-V4-Pro (0813, max reasoning)DeepSeek
68.8
$1.32 / $3.96
30 Gemini 3.1 Pro PreviewGoogle
68.8
$2 / $12
30 GLM-5.2 (max reasoning)Z.ai · best of 2 settings
68.8
$1.40 / $4.40
33 Qwen3.8-27B (extra-high reasoning)Alibaba · best of 4 settings
68.1
$0.50 / $3
34 Qwen3.7-MaxAlibaba
66.0
$1.48 / $4.42
35 DeepSeek-V4-Flash-Vision-Exp (max reasoning)DeepSeek
65.0
$0.22 / $0.65
36 Claude Sonnet 4.6 (max reasoning)Anthropic
63.0
$3 / $15
37 Kimi K2.6Moonshot AI
61.8
$0.95 / $4
38 Kimi K2.7 CodeMoonshot AI
60.8
$0.95 / $4
39 MiMo-V2.5-Pro (reasoning on)Xiaomi
60.2
$0.43 / $0.87
40 DeepSeek-V4-Pro (0423, max reasoning)DeepSeek · best of 2 settings
59.4
$1.42 / $2.83
41 Hy3Tencent
58.8
$0.14 / $0.58
42 Muse SparkMeta
58.6
–
42 MiniMax-M3MiniMax
58.6
$0.30 / $1.20
44 MiMo-V2.5Xiaomi
56.8
$0.40 / $2
45 DeepSeek-V4-Flash (0423, max reasoning)DeepSeek · best of 2 settings
56.2
$0.05 / $0.45
46 GPT-5.4 mini (extra-high reasoning)OpenAI
56.1
$0.75 / $4.50
46 GPT-5.4 nano (extra-high reasoning)OpenAI
56.1
$0.20 / $1.25
48 Qwen3.7-PlusAlibaba
55.9
$0.32 / $1.28
49 GLM-5.1Z.ai
55.8
$1.33 / $4.18
50 Qwen3.6-PlusAlibaba
54.5
$0.33 / $1.95
51 Qwen3.6-27BAlibaba · best of 2 settings
53.7
$0.30 / $3.20
52 Inkling SmallThinking Machines
52.9
$0.45 / $1.20
53 MiniMax-M2.7MiniMax
52.6
$0.30 / $1.20
54 Claude Sonnet 4.5 (reasoning on)Anthropic
52.1
$3 / $15
54 Inkling (extra-high reasoning)Thinking Machines
52.1
$1 / $4.05
56 Grok Build 0.1xAI
51.5
$1 / $2
57 GPT-5.1 (high reasoning)OpenAI
49.4
$1.25 / $10
58 Gemini 3.5 Flash-LiteGoogle
49.3
$0.30 / $2.50
59 Muse Glimmer (high reasoning)Meta
49.0
–
60 Qwen3.5-397B-A17BAlibaba
48.2
$0.55 / $3.50
61 Mistral Medium 3.5Mistral AI
46.9
$1.50 / $7.50
62 Kimi K2.5Moonshot AI
46.8
$0.57 / $2.85
63 GLM-4.6 (reasoning on)Z.ai
45.8
$0.50 / $2
64 Qwen3.5-122B-A10BAlibaba · best of 2 settings
45.7
$0.26 / $2.08
65 GLM-4.7Z.ai
45.3
$0.60 / $2.20
66 DeepSeek-V3.2 (reasoning on)DeepSeek
44.2
$0.28 / $0.42
67 Claude Haiku 4.5 (reasoning on)Anthropic
43.9
$1 / $5
68 DeepSeek-V3.1-Terminus (reasoning on)DeepSeek
43.5
$0.27 / $1
69 Gemma 4 31BGoogle · best of 2 settings
43.4
$0.15 / $0.40
70 Grok 4.3 (high reasoning)xAI · best of 2 settings
42.2
$1.25 / $2.50
71 Qwen3.6-35B-A3BAlibaba · best of 2 settings
41.9
$0.10 / $0.95
72 o1OpenAI
39.7
–
73 GPT-5.5 Instant (2026-06-26)OpenAI
39.4
–
74 Gemma 4 26B A4BGoogle
39.3
$0.09 / $0.30
75 GPT-5 (high reasoning)OpenAI
37.8
$1.25 / $10
76 Nemotron 3 Super 120B A12BNVIDIA
37.7
$0.08 / $0.45
77 Claude Sonnet 4 (reasoning on)Anthropic
37.6
–
78 Qwen3.5-35B-A3B (no reasoning)Alibaba
37.0
$0.15 / $1
79 Qwen3-Coder-NextAlibaba
36.2
$0.12 / $0.80
80 Gemini 3.1 Flash-Lite PreviewGoogle
34.7
$0.25 / $1.50
81 Gemini 2.5 ProGoogle
33.3
$1.25 / $10
82 Devstral 2Mistral AI
31.3
$0.40 / $2
83 Mercury 2Inception
31.1
–
84 Gemma 4 12BGoogle
31.0
–
85 gpt-oss-120b (high reasoning)OpenAI · best of 2 settings
30.4
$0.10 / $0.50
86 Devstral Small 2Mistral AI
29.3
–
87 Qwen3.5-9BAlibaba · best of 2 settings
28.7
$0.10 / $0.15
88 Mistral Small 4Mistral AI
26.6
$0.15 / $0.60
89 Mistral Small 3.1 24BMistral AI
26.3
$0.35 / $0.56
90 Trinity Large ThinkingArcee AI
25.8
–
91 DeepSeek-R1DeepSeek
24.6
–
92 GPT-4o (2024-05-13)OpenAI
24.2
$5 / $15
93 Nova 2 Lite (high reasoning)Amazon
23.0
$0.30 / $2.50
93 DeepSeek-V3DeepSeek
23.0
$0.26 / $1.03
95 Qwen3.5-4B (reasoning on)Alibaba · best of 2 settings
22.6
–
96 Granite 4.2 8BIBM
22.4
$0.06 / $0.15
97 Qwen3-235B-A22B-Thinking-2507Alibaba
22.1
$0.45 / $3.50
98 Magistral Medium 1.2Mistral AI
21.3
–
99 DeepSeek-V3-0324DeepSeek
21.2
$0.25 / $1
100 gpt-oss-20b (high reasoning)OpenAI
20.7
$0.03 / $0.14
101 Mistral Medium 3.1Mistral AI
20.5
$0.40 / $2
102 GPT-4.1 miniOpenAI
20.2
$0.40 / $1.60
103 Mistral Large 3Mistral AI
20.1
$0.50 / $1.50
104 DiffusionGemma 26B A4BGoogle
19.7
–
105 Qwen3-Next-80B-A3B-ThinkingAlibaba
17.4
–
106 Llama 4 MaverickMeta
16.3
$0.35 / $1
106 o3-mini (high reasoning)OpenAI
16.3
–
108 Solar Pro 3Upstage
16.2
–
109 GPT-5 mini (high reasoning)OpenAI
15.6
$0.25 / $2
110 Qwen3-32B (reasoning on)Alibaba
15.3
$0.14 / $0.40
111 Magistral Small 1.2Mistral AI
14.7
–
112 Ministral 3 14BMistral AI
14.4
$0.20 / $0.20
112 Nemotron 3 Nano 30B A3B (reasoning on)NVIDIA
14.4
$0.06 / $0.24
114 Qwen3-14B (reasoning on)Alibaba
13.8
$0.10 / $0.22
115 Mistral Small 3.2 24BMistral AI
12.5
$0.094 / $0.25
116 Qwen3-30B-A3B-Thinking-2507Alibaba
12.1
–
117 Llama 3.3 70B InstructMeta
11.9
$0.71 / $0.71
118 GPT-4o mini (2024-07-18)OpenAI
11.4
$0.15 / $0.60
119 GPT-4.1 nanoOpenAI
11.1
$0.10 / $0.40
120 Gemma 3 27BGoogle
10.1
$0.08 / $0.35
121 Ministral 3 8BMistral AI
9.7
$0.15 / $0.15
122 Qwen3-8B (reasoning on)Alibaba
9.0
–
123 Llama 4 ScoutMeta
8.2
$0.10 / $0.30
124 Gemma 4 E2BGoogle
7.2
–
125 Gemma 3 12BGoogle
5.8
$0.05 / $0.15
126 Llama 3.1 8B InstructMeta
5.4
$0.05 / $0.08
127 Ministral 3 3BMistral AI
4.8
$0.10 / $0.10
128 Qwen3.5-2B (reasoning on)Alibaba · best of 2 settings
2.9
–
129 Gemma 3 4BGoogle
2.7
$0.04 / $0.05
130 Qwen3.5-0.8B (no reasoning)Alibaba · best of 2 settings
1.2
–

Swipe the table sideways for more columns.

Source: Artificial Analysis, via Spring Prompt, springprompt.com/benchmarks/artificial-analysis. Test your own prompt on these models →

Ranks follow the score as shown, so equal numbers share a rank. Each model is shown at its best setting; show every setting. Results as published by Artificial Analysis; we do not re-run them.

Progress over time

Artificial Analysis Coding Index, plotted at each model's release date, higher is better. Each model counts once, at its best setting. Scores are today's, not launch day's. Hover or tap a mark for its model.

Best score so far

Every model at its release date. The line moves each time a new release beats every earlier one, and each new best is named where there is room.

050100 Jul 20242025Jul2026Jul GPT-4o (2024-05-13)o1DeepSeek-V3.1-TerminusClaude Sonnet 4.5Claude Sonnet 4.6Gemini 3.1 Pro PreviewGPT-5.4Claude Fable 5GPT-5.6 SolClaude Fable 5.1

Best score by lab

Each lab's best so far, stepping whenever one of its releases beats its own earlier models. The 6 labs with the best scores today; 14 others not drawn.

AnthropicOpenAIxAIMetaGoogleAlibaba

020406080100 Jul 20242025Jul2026Jul AnthropicOpenAIxAIMetaGoogleAlibaba

What it measures

Artificial Analysis's blend of its coding evaluations.

What it does not measure

Not your codebase or tools.

291 results from Artificial Analysis not ranked here · show why

We rank a result only when we can tie it to a specific model you can use. These are left out:

  • Not on sale through the API providers we track: 276
  • A different snapshot or variant from the model we list: 14
  • An unusual combination of settings: 1

Data sourced from Artificial Analysis. Licence: Artificial Analysis commercial data licence.