Category
Coding models
The strongest models for code generation, refactoring, debugging, and multi-file edits, based on public coding benchmarks and LMRank ranking.
Our picks
Editorial picks, in the order we recommend them.| Model | Rank | Context | Input price |
|---|---|---|---|
| Claude Fable 5Anthropic | #1 | 1M | $10.00/1M |
| DeepSeek V4 Pro previewDeepSeek | #17 | 1M | $0.42/1M |
| GPT-5.3-CodexOpenAI | #51 | 400K | $1.75/1M |
More ranked coding models
Other models that fit this category, in leaderboard order.| Model | Rank | Context | Input price |
|---|---|---|---|
| GPT-5.6 SolOpenAI | #4 | 1.1M | $2.00/1M |
| GPT-5.5 ProOpenAI | #6 | 1.1M | $30.00/1M |
| Claude Sonnet 5Anthropic | #7 | 1M | $2.00/1M |
| GPT-5.6 TerraOpenAI | #12 | 1.1M | $2.00/1M |
| Claude Opus 4.6Anthropic | #13 | 1M | $5.00/1M |
| GLM 5.2Z.ai | #14 | 1M | $0.65/1M |
| GLM 5.1Z.ai | #15 | 204.8K | $0.96/1M |
| Claude Sonnet 4.6Anthropic | #16 | 1M | $3.00/1M |
| GPT-5.4OpenAI | #19 | 1.1M | $2.50/1M |
| GPT-5.6 LunaOpenAI | #20 | 1.1M | $0.20/1M |
| GLM 5Z.ai | #22 | 204.8K | $0.60/1M |
| Claude Sonnet 4Anthropic | #23 | 200K | $3.00/1M |