CtrlAltDebrief

Coding Index benchmark

185 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.

Scores frozen

Claude Fable 5.1 (Anthropic) leads at 81.6

Artificial Analysis last published scores for this benchmark on Sep 9, 2026. Scores here are frozen at that date, and models released since are not on it.
Data via Artificial Analysis methodology →

Models ranked

185

on this benchmark

Top score

81.6

on the frozen board

Type

Composite

index

Frozen

Sep 9, 2026

benchmark scores

Cost vs Coding Index

122 priced models
Most attractive quadrant (cheap + high)
= reasoning model (extended thinking)
01734516885$0.03$0.1$0.3$1$3$10$30COST / 1M INPUT TOKENS (log) →CODING INDEX SCORE ↑Claude Fable 5.1GPT-5.6 SolClaude Opus 5GPT-6 AstraGrok 4.6GPT-5.6 TerraClaude Fable 5Gemini 3.8 FlashKimi K3GLM 5.3GLM 5.2Qwen3.8 27BinclusionAI: Ling 3.0 Flashgpt-oss-20bLlama 3.1 8B Instruct

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 · 185 models
Maker
#
1Claude Fable 5.1Anthropic81.6
$10.00
via Anthropic
$50.00
via Anthropic
2GPT-5.6 SolOpenAI78.3xhigh
$2.00
Routed quote
$10.00
Routed quote
3Claude Opus 5Anthropic78.0
$5.00
via Anthropic
$25.00
via Anthropic
4GPT-6 AstraOpenAI76.9
$10.00
via OpenAI
$50.00
via OpenAI
5Grok 4.6xAI76.8
$2.00
via xAI
$6.00
via xAI
6GPT-5.6 TerraOpenAI76.7
$2.00
via OpenAI
$12.00
via OpenAI
7Claude Fable 5Anthropic76.5
$10.00
via Anthropic
$50.00
via Anthropic
8Gemini 3.8 FlashGoogle76.3
$0.75
via Google
$3.75
via Google
9Kimi K3Moonshot76.2
$0.70
Routed quote
$12.50
via Sail
10Gemini 3.7 FlashGoogle76.1
$0.75
via Google
$3.75
via Google
11Muse Spark 1.3Other75.8
$1.25
via Azure
$4.25
via Azure
12GPT-5.5OpenAI74.9
$5.00
via OpenAI
$30.00
via OpenAI
13GLM 5.3Zhipu74.8
$0.079
Routed quote
$3.08
via Sail
14Claude Opus 4.8Anthropic74.3
$5.00
via Anthropic
$25.00
via Anthropic
15Claude Opus 4.7Anthropic73.6
$5.00
via Anthropic
$25.00
via Anthropic
16Qwen3.8-Flash-NextAlibaba73.1
n/a
n/a
17Grok 4.5xAI72.4
$2.00
via xAI
$6.00
via xAI
18Muse Spark 1.2Other72.2
$1.25
via Meta
$4.25
via Meta
19Qwen3.8 2.4T A95BAlibaba71.9
$2.00
via Aihubmix
$6.00
via Aihubmix
20Claude Sonnet 5Anthropic71.5
$2.00
via Anthropic
$10.00
via Anthropic
21GLM 5.3 FlashZhipu71.5
$0.11
via Sail
$0.35
via Sail
22GPT-5.6 LunaOpenAI71.4
$0.20
via OpenAI
$1.20
via OpenAI
23Muse Spark 1.1Other71.3
$1.25
via Meta
$4.25
via Meta
24GPT-5.4OpenAI71.1
$2.50
via Databricks
$15.00
via OpenAI
25Gemini 3.5 FlashGoogle70.1
$1.50
via Google
$9.00
via Google
26Gemini 3.6 FlashGoogle69.2
$0.75
via Google
$3.75
via Google
27Gemini 3.1 Pro PreviewGoogle68.8
$2.00
via Google
$12.00
via Google
28GLM 5.2Zhipu68.8
$0.05
Routed quote
$1.98
via Scx AI
29Qwen3.8 27BAlibaba68.1
$0.04
Routed quote
$1.49
via Cerebras
30Qwen3.7 MaxAlibaba66.0
$1.25
via Novita
$3.75
via Novita
31DeepSeek V4 Flash Vision (Reasoning, Max Effort)DeepSeek65.0
n/a
n/a
32Motif 3Motif-technologies63.5
n/a
n/a
33Claude Sonnet 4.6Anthropic63.0reasoning: adaptive
$3.00
via Databricks
$15.00
via Anthropic
34Agnes 2.5 Pro BetaSapiens-ai62.3
n/a
n/a
35Motif 3 (Beta) (0714)Motif-technologies62.0
n/a
n/a
36Kimi K2.6Moonshot61.8
$0.65
via Wandb
$3.40
via Novita
37K2 Horizon 375B A23BMbzuai-institute-of-foundation-models61.5
n/a
n/a
38Quasar 438BMultiverse-computing61.2
n/a
n/a
39Kimi K2.7 CodeMoonshot60.8
$0.671
Routed quote
$3.35
Routed quote
40Apodex 1.1Apodex60.8
n/a
n/a
41MiMo-V2.5-ProXiaomi60.2
$0.435
Routed quote
$0.87
Routed quote
42KAT-Coder-Pro V2Other59.5
$0.30
Routed quote
$1.20
Routed quote
43Nex-N2-ProOther59.1
$0.25
Routed quote
$1.00
Routed quote
44Hy3Tencent58.8
$0.132
Routed quote
$0.528
Routed quote
45Agnes 2.5 Pro AlphaSapiens-ai58.8
n/a
n/a
46Muse SparkMeta58.6
n/a
n/a
47MiniMax M3MiniMax58.6
$0.23
via Wandb
$0.96
via Wandb
48GPT-5.4 MiniOpenAI56.1
$0.75
via Databricks
$4.50
via OpenAI
49GPT-5.4 NanoOpenAI56.1
$0.20
via Databricks
$1.25
via Databricks
50Qwen3.7 PlusAlibaba55.9
$0.282
via Aihubmix
$1.13
via Aihubmix
1–50 of 185
Page 1 of 4
On-demand listed rates, OpenRouter routed quotes and Vercel reseller quotes. Enterprise commitments can be materially lower. Cost per task uses best-effort token usage. An OpenRouter routed quote is the price of whichever upstream provider OpenRouter prefers today, so it moves day to day.

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?

Claude Fable 5.1 (Anthropic) leads with 81.6, from $10.00 per 1M input tokens from Anthropic. Artificial Analysis last published scores for this benchmark on Sep 9, 2026. Scores here are frozen at that date, and models released since are not on it.

How many models are ranked on Coding Index?

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

Other benchmarks

compare the same models on a different eval
Intelligence Indexcomposite indexAgentic Indexcomposite indexGPQA DiamondleaderboardHumanity's Last ExamleaderboardMMLU-ProleaderboardMMMU-ProleaderboardLiveCodeBenchleaderboardSciCodeleaderboardTerminalBench HardleaderboardTerminalBench v2.1leaderboardτ²-benchleaderboardτ-bench BankingleaderboardAPEX AgentsleaderboardIT-Bench SREleaderboardGDPvalleaderboardCritPtleaderboardOmniscienceleaderboardIFBenchleaderboardLong-Context Reasoningcomposite indexSWE-bench VerifiedleaderboardSWE-bench ProleaderboardAIME 2026leaderboardARC-AGI-2leaderboardAA-Briefcaseleaderboard
Benchmark scores via Artificial Analysis · last published Sep 9, 2026 · Listed prices from LiteLLM, OpenRouter and Vercel · catalogue refreshed Oct 14, 2026 · 77 prices older, back to Jul 19, 2026

Every weekday

AI moves fast. Here's your debrief.

News, analysis, tools, and more.

For people who build with AI