Code & Software Engineering

Artificial Analysis public leaderboard

Coding Index

Artificial Analysis composite index for programming and software-engineering capability.

Published source

Metric

Index score

Results shown

256

Publisher

Artificial Analysis

Snapshot

Fetched 2026-09-08T22:57:37.545Z

256 of 256 models

Higher is better

Claude Fable 5.1 (max with fallback)

Claude Fable 5.1 (xhigh with fallback)

Claude Fable 5.1 (high with fallback)

GPT-5.6 Sol (xhigh)

Claude Opus 5 (max)

GPT-5.6 Sol (max)

GPT-5.6 Sol (high)

GPT-6 Astra (high)

Claude Fable 5.1 (medium with fallback)

Claude Opus 5 (xhigh)

GPT-6 Astra (max)

Grok 4.6 (high)

GPT-6 Astra (medium)

GPT-5.6 Terra (max)

Claude Opus 5 (high)

Claude Fable 5 (with fallback)

Muse Spark 1.3 (xhigh)

Gemini 3.8 Flash (high)

GPT-5.6 Sol (medium)

GPT-6 Astra (Non-reasoning)

Kimi K3 (max)

Gemini 3.7 Flash (high)

GPT-6 Astra (xhigh)

Grok 4.6 (xhigh)

Muse Spark 1.3 (max)

GPT-6 Astra (low)

Claude Fable 5.1 (low with fallback)

GPT-5.5 (xhigh)

GLM-5.3 (max)

Grok 4.6 (medium)

Claude Opus 5 (medium)

Claude Opus 4.8 (max)

Gemini 3.8 Flash (medium)

Claude Opus 4.7 (max)

Gemini 3.8 Flash (low)

Qwen3.8-Flash-Next

Grok 4.5 (high)

Muse Spark 1.2 (xhigh)

Kimi K3 (low)

Qwen3.8 2.4T A95B

Qwen3.8 Max

GPT-5.5 (high)

Claude Sonnet 5 (max)

GLM-5.3-Flash

GPT-5.5 (medium)

Gemini 3.7 Flash (medium)

GPT-5.6 Luna (max)

Muse Spark 1.1 (xhigh)

GPT-5.4 (xhigh)

Gemini 3.7 Flash (low)

GPT-5.6 Terra (xhigh)

Gemini 3.5 Flash

GPT-5.6 Sol (low)

Gemini 3.6 Flash

DeepSeek V4 Flash 0731 (max)

DeepSeek V4 Pro 0813 (max)

Gemini 3.1 Pro Preview

GLM-5.2 (max)

GPT-5.6 Luna (xhigh)

Qwen3.8 27B (xhigh)

GPT-5.6 Terra (high)

Claude Opus 5 (low)

Claude Sonnet 5 (Non-reasoning)

Grok 4.6 (low)

Qwen3.7 Max

GPT-5.6 Sol (Non-reasoning)

DeepSeek V4 Flash Vision (max)

GPT-5.6 Terra (medium)

Motif 3

GPT-5.6 Luna (high)

Claude Sonnet 4.6 (max)

Agnes 2.5 Pro Beta

Motif 3 (Beta)

Kimi K2.6

K2 Horizon 375B A23B

Quasar 438B (max)

GPT-5.5 (low)

Kimi K2.7 Code

Apodex 1.1

MiMo-V2.5-Pro

KAT-Coder-Pro V2

DeepSeek V4 Pro (max)

Nex-N2-Pro

Hy3

Agnes 2.5 Pro Alpha

DeepSeek V4 Pro (high)

Muse Spark

MiniMax-M3

Qwen3.8 27B (low)

GPT-5.6 Terra (low)

MiMo-V2.5

GPT-5.5 (Non-reasoning)

DeepSeek V4 Flash (max)

Qwen3.8 27B (medium)

GPT-5.4 mini (xhigh)

GPT-5.4 nano (xhigh)

Qwen3.7 Plus

GLM-5.1

Qwen3.6 Plus

Qwen3.6 27B

Inkling Small

Solar Pro 4

MiniMax-M2.7

JT-4.1 Flash 236B A21B

GPT-5.6 Terra (Non-reasoning)

Claude 4.5 Sonnet

Inkling

DeepSeek V4 Flash (high)

Grok Build 0.1 0616

GPT-5.6 Luna (medium)

Ling 3.0 Flash

MiMo-V2-Flash (Non-reasoning)

GPT-5.1 (high)

Gemini 3.5 Flash-Lite

Nemotron 3 Ultra

Muse Glimmer (high)

Qwen3.5 397B A17B

Mistral Medium 3.5

Kimi K2.5

Gemini 2.5 Pro (Mar)

Qwen3.6 27B (Non-reasoning)

GLM-5.2 (Non-reasoning)

GLM-4.6

Qwen3.5 122B A10B

LongCat 2.0

GLM-4.7

Solar Open2 250B

Qwen3.8 27B

DeepSeek V3.2

GPT-5.6 Luna (low)

Claude 4.5 Haiku

DeepSeek V3.1 Terminus

Gemma 4 31B

Qwen3.5 122B A10B (Non-reasoning)

Ring-2.6-1T

Grok 4.3 (high)

Qwen3.6 35B A3B

K-

K-EXAONE 2.0

Step 3.7 Flash

GPT-5.5 Instant (June 2026)

Gemma 4 26B A4B

GPT-5.6 Luna (Non-reasoning)

A.X-K2

GPT-5 (high)

Nemotron 3 Super

Claude 4 Sonnet

Qwen3.5 35B A3B (Non-reasoning)

North Mini Code

Claude 3.7 Sonnet

Qwen3 Coder Next

Grok 4.3 (Non-reasoning)

Gemini 3.1 Flash-Lite

o1-preview

Nova 2.0 Pro Preview (medium)

Gemini 2.5 Pro

Gemma 4 31B (Non-reasoning)

G9v3-39A5B

K-

K-EXAONE

Devstral 2

Mercury 2

Gemma 4 12B

gpt-oss-120b (high)

Claude 3.5 Sonnet (Oct)

Granite 4.2 30B

Devstral Small 2

Qwen3.5 9B

Qwen3.6 35B A3B (Non-reasoning)

Command A+

Nemotron 3.5 Lightning

Mistral Small 4

Ling 3.0 Tiny

Mistral Small 3.1

Claude 3.5 Sonnet (June)

Nova 2.0 Pro Preview (low)

Trinity Large Thinking

Gemini 2.0 Pro Experimental

Nemotron Cascade 2 30B A3B

Ling 2.6 Flash

DeepSeek R1 (Jan)

GPT-4o (May)

Gemini 2.0 Flash Thinking exp. (Jan)

Gemini 1.5 Pro (Sep)

EXAONE 4.5 33B

Qwen3.5 9B (Non-reasoning)

HyperNova 60B 2605 (high)

Nova 2.0 Lite (high)

DeepSeek V3 (Dec)

Qwen3.5 4B

Granite 4.2 8B

Qwen3 235B A22B 2507

GPT-4 Turbo

Magistral Medium 1.2

gpt-oss-120b (low)

DeepSeek V3 0324

K2 Think V2

Nova 2.0 Pro Preview (Non-reasoning)

gpt-oss-20b (high)

Mistral Medium 3.1

Qwen3.5 4B (Non-reasoning)

GPT-4.1 mini

Mistral Large 3

Gemini 1.5 Pro (May)

DiffusionGemma 26B A4B

Claude 3 Opus

Gemini 1.0 Ultra

Granite 4.2 3B

Qwen3 Next 80B A3B (Reasoning)

Llama 4 Maverick

o3-mini (high)

Solar Pro 3

Claude 3.5 Haiku

GPT-5 mini (high)

Qwen3 32B

Magistral Small 1.2

MiniCPM5-2B

Celeris-1

Nemotron 3 Nano

Ministral 3 14B

Claude 2.1

Qwen3 14B

Nemotron 3 Nano Omni 30B A3B

GPT-4

Claude 2.0

Mistral Small 3.2

Qwen3 30B A3B 2507

Llama 3.3 70B

GPT-4o mini

GPT-4.1 nano

GPT-3.5 Turbo

Granite 4.1 30B

Gemma 3 27B

G9v3-3B

Ministral 3 8B

Nanbeige4.1-3B

Granite 4.1 8B

Gemma 4 E4B

Qwen3 8B

Llama 4 Scout

Nemotron 3 Nano 4B

Claude Instant

LFM2.5-2.6B

Gemma 4 E2B

Gemma 3 12B

Llama 3.1 8B

Ministral 3 3B

Granite 4.1 3B

PALM-2

Phi-4 Mini

Gemma 3n E4B

Qwen3.5 2B

Gemma 3 4B

Qwen3.5 2B (Non-reasoning)

Qwen3.5 0.8B (Non-reasoning)

MiniCPM-V 4.6 1.3B

Qwen3.5 0.8B

List bars visualize relative performance. Plot bars use published 0–100 scores, shrink to a 1.5rem minimum, then scroll horizontally.

Scores are published snapshots and are only comparable within the same benchmark, version, metric, and evaluation configuration.