Artificial Analysis Coding Index
Indexes · 2025-02-13
Composite index of coding and software engineering benchmarks.
Top models (higher is better)
| Model | Score |
|---|---|
| GPT-5.6 Sol | 78.3 |
| GPT-5.6 Terra | 76.7 |
| Claude Fable 5 | 76.5 |
| Kimi K3 | 76.2 |
| GPT-5.5 | 74.9 |
| Opus 4.8 | 74.3 |
| Opus 4.7 | 73.6 |
| Grok 4.5 | 72.4 |
| Sonnet 5 | 71.5 |
| GPT-5.6 Luna | 71.4 |
| Muse Spark 1.1 | 71.3 |
| GPT-5.4 | 71.1 |
| Gemini 3.5 Flash | 70.1 |
| Gemini 3.6 Flash | 69.2 |
| DeepSeek-V4-Flash-0731 | 69.1 |
| Gemini 3.1 Pro Preview | 68.8 |
| GLM-5.2 | 68.8 |
| Qwen3.7-Max | 66.0 |
| Sonnet 4.6 | 63.0 |
| Motif-3-Beta | 62.0 |
| Kimi K2.6 | 61.8 |
| Kimi K2.7 Code | 60.8 |
| MiMo-V2.5-Pro | 60.2 |
| KAT-Coder-Pro V2 | 59.5 |
| DeepSeek-V4-Pro | 59.4 |
| Nex-N2-Pro | 59.1 |
| Hy3 | 58.8 |
| Agnes 2.5 Pro Alpha | 58.8 |
| Muse Spark | 58.6 |
| MiniMax M3 | 58.6 |
| MiMo-V2.5 | 56.8 |
| DeepSeek-V4-Flash | 56.2 |
| GPT-5.4 Mini | 56.1 |
| GPT-5.4 Nano | 56.1 |
| Qwen3.7-Plus | 55.9 |
| GLM-5.1 | 55.8 |
| Qwen3.6 Plus (2026-04-02) | 54.5 |
| Qwen3.6 27B | 53.7 |
| Inkling-Small | 52.9 |
| MiniMax M2.7 | 52.6 |