Category
Coding Models
The strongest models for code generation, refactoring, debugging, and multi-file edits, based on public coding benchmarks and LMRank ranking.
3 models
← All categories
Top Coding models
| Model | Pricing |
|---|---|
| Claude Fable 5 Anthropic | $10.00/1M input |
| DeepSeek V4 Pro preview DeepSeek | $0.44/1M input |
| GPT-5.3-Codex OpenAI | $1.75/1M input |
How these models were selected
Picks combine leaderboard position with published coding results, repository-scale editing ability, tool use, and evidence from agentic software-engineering tasks.
When to use a different shortlist
Coding strength can come with higher output cost or slower responses. For autocomplete and small edits, a fast budget model may be more useful than the strongest agentic model.
Open each model page to verify current pricing, context limits, source links, and known limitations before choosing a provider.