Coding Index benchmark

136 AI models ranked on Coding Index. Each row shows the model’s score next to its cheapest API price per 1M tokens where it has one, so you can weigh quality against cost.

Top model today

GPT-5.6 Sol (OpenAI) leads at 78.3, from $5.00 per 1M input.

Data via Artificial Analysis

Models ranked

136

on this benchmark

Top score

78.3

current leader

Type

Composite

index

Updated

15 July 2026

last source fetch

Cost vs Coding Index

83 priced models
Most attractive quadrant (cheap + high)
= reasoning model (extended thinking)

Each labelled name links to that model’s page. Curated to the cost-efficiency frontier, top scorers and cheapest so labels stay readable; the full field is in the leaderboard table below (and via “select all”). Reasoning models (extended “thinking” before answering) carry a ring around the dot.

Models ranked on Coding Index

highest score first · 136 models
Maker
#
1GPT-5.6 SolOpenAI78.3xhigh$5.00$30.00
2GPT-5.6 TerraOpenAI76.7$2.50$15.00
3Claude Fable 5Anthropic76.5$10.00$50.00
4GPT-5.5OpenAI74.9$5.00$30.00
5Claude Opus 4.8Anthropic74.3$5.00$25.00
6Claude Opus 4.7Anthropic73.6$5.00$25.00
7Grok 4.5xAI72.4$2.00$6.00
8Claude Sonnet 5Anthropic71.5$2.00$10.00
9GPT-5.6 LunaOpenAI71.4$1.00$6.00
10Muse Spark 1.1Other71.3$1.25$4.25
11GPT-5.4OpenAI71.1$2.50$15.00
12Gemini 3.5 FlashGoogle70.1$1.50$9.00
13Gemini 3.1 Pro PreviewGoogle68.8$2.00$12.00
14GLM 5.2Zhipu68.8$1.40$4.40
15Qwen3.7 MaxAlibaba66.0n/an/a
16Claude Sonnet 4.6Anthropic63.0reasoning: adaptive$3.00$15.00
17Kimi K2.6Moonshot61.8n/an/a
18Kimi K2.7 CodeMoonshot60.8$0.95$4.00
19MiMo-V2.5-ProXiaomi60.2$1.00$3.00
20KAT-Coder-Pro V2Other59.5$0.30$1.20
21DeepSeek V4 ProDeepSeek59.4$0.43$0.87
22Nex-N2-ProNex-agi59.1n/an/a
23Hy3-previewTencent58.8n/an/a
24Muse SparkMeta58.6n/an/a
25MiniMax M3MiniMax58.6$0.30$1.20
26MiMo-V2.5Xiaomi56.8n/an/a
27DeepSeek V4 FlashDeepSeek56.2n/an/a
28GPT-5.4 MiniOpenAI56.1$0.75$4.50
29GPT-5.4 NanoOpenAI56.1$0.20$1.25
30Qwen3.7 PlusAlibaba55.9n/an/a
31GLM 5.1Zhipu55.8$1.05$3.50
32Qwen3.6 PlusAlibaba54.5$0.33$1.95
33Qwen3.6 27BAlibaba53.7$0.15$0.50
34MiniMax M2.7MiniMax52.6$0.26$0.55
35JT-4.1 Flash 236B A21BChina-mobile52.4n/an/a
36Claude 4.5 SonnetAnthropic52.1reasoning: true$3.00$15.00
37Grok Build 0.1 0616Spacexai51.5n/an/a
38Mimo V2 FlashXiaomi49.8$0.10$0.30
39GPT-5.1OpenAI49.4$1.25$10.00
40Nemotron 3 UltraNVIDIA49.3n/an/a
41Qwen3.5 397B A17BAlibaba48.2$0.60$3.60
42Mistral Medium 3.5Mistral46.9$1.50$7.50
43Kimi K2.5Moonshot46.8$0.50$2.80
44Gemini 2.5 Pro (Mar)Google46.7n/an/a
45GLM 4.6Zhipu45.8reasoning: true$0.40$1.75
46Qwen3.5-122B-A10BAlibaba45.7$0.25$1.75
47LongCat 2.0Longcat45.3n/an/a
48GLM 4.7Zhipu45.3$0.40$1.50
49DeepSeek V3.2DeepSeek44.2reasoning: true$0.27$0.40
50Claude 4.5 HaikuAnthropic43.9reasoning: true$1.00$5.00
150 of 136
Page 1 of 3
Prices are on-demand list rates. Enterprise commitments can be materially lower. Cost per task uses best-effort token usage.

Frequently asked questions

What is the Coding Index benchmark?

Artificial Analysis's composite coding score (0 to 100), averaging coding evaluations such as Terminal-Bench (terminal-based software-engineering and sysadmin tasks) and SciCode (scientific-computing Python problems) and normalising to a 0 to 100 scale. Higher means stronger overall coding performance.

Which AI model scores highest on Coding Index?

GPT-5.6 Sol (OpenAI) leads with 78.3, from $5.00 per 1M input tokens.

How many models are ranked on Coding Index?

136 models carry a Coding Index score. Scores come from Artificial Analysis; where a model has a live API price it is verified against LiteLLM and OpenRouter, and models with no current price are listed without one.

Other benchmarks

compare the same models on a different eval
Benchmark scores via Artificial Analysis · pricing verified against LiteLLM + OpenRouter · refreshed daily · updated 15 July 2026

Every weekday

AI moves fast. Here's your debrief.

News, analysis, tools, and more.

For people who build with AI