Best LLMs for Coding
The best LLMs for coding are ranked here by their scores on coding benchmarks — measuring code generation, bug fixing, and software-engineering ability. A higher score means stronger performance on programming tasks. Pair benchmark strength with context window (for large codebases) and price when choosing a coding model.
Ranked list (top 25)
| # | Model | Coding score | Input / 1M | Output / 1M | Context |
|---|---|---|---|---|---|
| 1 | Anthropic: Claude Opus 5.5 Anthropic | 1811.2 | $4.00 | $20.00 | 1M |
| 2 | OpenAI: GPT-6 Astra OpenAI | 1780.2 | $10.00 | $50.00 | 1.1M |
| 3 | Anthropic: Claude Sonnet 5.5 Anthropic | 1773.7 | $2.00 | $10.00 | 1M |
| 4 | OpenAI: GPT-6.1 Sol OpenAI | 1760.1 | $2.00 | $10.00 | 1.1M |
| 5 | Anthropic: Claude Fable 5.1 Anthropic | 1742.7 | $10.00 | $50.00 | 1M |
| 6 | Anthropic: Claude Opus 5 Anthropic | 1690.0 | $5.00 | $25.00 | 1M |
| 7 | OpenAI: GPT-6 Sol OpenAI | 1685.9 | $2.00 | $10.00 | 1.1M |
| 8 | Google: Gemini 4 Argon Google | 1678.0 | $2.00 | $10.00 | 1M |
| 9 | Qwen3.8 Max Alibaba | 1673.2 | $2.00 | $6.00 | 1M |
| 10 | Meta: Muse Spark 1.3 Meta | 1658.5 | $1.25 | $4.25 | 1M |
| 11 | MoonshotAI: Kimi K3 MoonshotAI | 1655.3 | $0.45 | $15.00 | 1M |
| 12 | Meta: Muse Wonder Meta | 1651.0 | $4.00 | $20.00 | 1M |
| 13 | SpaceXAI: Grok 4.7 SpaceXAI | 1640.2 | $2.00 | $6.00 | 500K |
| 14 | Xiaomi: MiMo-V2.6-Flash Xiaomi | 1635.1 | $0.14 | $0.28 | 1.1M |
| 15 | Qwen3.8 Flash Next AMDOpen weights | 1633.2 | $0.15 | $0.47 | 262K |
| 16 | Tencent: Hy4 preview Tencent | 1631.6 | $0.83 | $2.50 | 1M |
| 17 | Xiaomi: MiMo-V2.6-Pro Xiaomi | 1625.2 | $0.44 | $0.87 | 1.1M |
| 18 | Anthropic: Claude Fable 5 Anthropic | 1623.8 | $10.00 | $50.00 | 1M |
| 19 | Z.ai: GLM 5.3 Z.ai | 1621.2 | $0.08 | $4.80 | 1M |
| 20 | DeepSeek: DeepSeek V4.1 Flash DeepSeek | 1618.5 | $0.01 | $0.89 | 1M |
| 21 | SpaceXAI: Grok 4.6 SpaceXAI | 1617.4 | $2.00 | $6.00 | 500K |
| 22 | OpenAI: GPT-5.6 Sol OpenAI | 1617.0 | $4.00 | $20.00 | 1.1M |
| 23 | Z.ai: GLM 5.3 Flash Z.ai | 1606.0 | $0.04 | $0.90 | 1M |
| 24 | Z.ai: GLM 5.2 Z.ai | 1604.1 | $0.04 | $7.00 | 1M |
| 25 | Qwen: Qwen3.8 27B Qwen | 1594.2 | $0.24 | $2.20 | 1M |
Prices are per 1M tokens (USD); confirm with the provider. Updated regularly.
More LLM rankings
Frequently asked questions
What is the best LLM for coding?
Based on coding benchmark scores, Anthropic: Claude Opus 5.5 ranks at the top in our dataset. See the full ranking above.
How are coding LLMs ranked?
Models are ranked by their score on coding-category benchmarks (such as code generation and software-engineering tasks). Higher scores indicate stronger coding ability.
Does context window matter for coding?
Yes — a larger context window lets a model see more of your codebase at once, which helps with multi-file edits and understanding project-wide context. Balance benchmark score with context size.