# Weekly coding model ranking, by BenchLM

This week's top 10 models on BenchLM's coding ranking, renewed every week.

- Language: en
- Published: 2026-10-30
- Tags: automation, coding-models, benchmark
- URL: https://devs7ud.io/en/rankings/ranking-coding-models-weekly-en
- Translation (ko): https://devs7ud.io/rankings/ranking-coding-models-weekly.md

- Ranking: weekly, as of 2026-10-29
- Source: BenchLM - https://benchlm.ai/coding
- Basis: This is BenchLM's coding ranking: a weighted composite of coding benchmarks such as SWE-bench Pro, DeepSWE and CursorBench \(BenchAlign v5.8\), copied as the source published it on the date shown. Other rankings may differ.

1. Claude Opus 5.5 (82\.9) - https://www.anthropic.com/news/claude-opus-5-5 - Anthropic
2. Claude Sonnet 5.5 (81\.7) - https://platform.claude.com/docs/en/models/overview - Anthropic
3. Gemini 4 Carbon (81\.1) - https://ai.google.dev/gemini-api/docs/models - Google · Not yet listed in Google's model docs
4. Claude Fable 5.1 (76\.4) - https://platform.claude.com/docs/en/models/overview - Anthropic
5. GPT-6 Astra (74\.7) - https://developers.openai.com/api/docs/models/gpt-6-astra - OpenAI
6. Gemini 4 Argon (72\.2) - https://ai.google.dev/gemini-api/docs/models/gemini-4-argon - Google
7. Claude Fable 5 (71\.4) - https://platform.claude.com/docs/en/models/overview - Anthropic
8. Muse Wonder Full (71\.1) - https://research.meta.ai/blog/muse-wonder - Meta
9. Claude Opus 5 (70\.5) - https://platform.claude.com/docs/en/models/overview - Anthropic
10. GPT-6.1 Sol (70\.3) - https://developers.openai.com/api/docs/models/gpt-6.1-sol - OpenAI

Scores are copied as the source published them. The same model name can score differently depending on the agent tool it runs in, so rankings differ from source to source. Each button goes to the model's official page.