Best AI Coding Agents. Averaged from four coding benchmarks.
Coding benchmarks test different skills: working in a terminal, migrating code, building an app from scratch. We average a model's position across all of them and update the list every week.
Coding agent ranking
Ranked by average position across four coding benchmarks.
As of November 3, 2026, Claude Sonnet 5.5 holds first place on the coding board, with an average rank of 1.75 across 4 boards, ahead of Claude Opus 5.5 (2.25).
Benchmarks where the agent has to produce working software. A model needs a rank on at least 3 of these 4 boards to be listed.
| Rank | Model | Average rank | Terminal-Bench 4.0 | Code Migration | Vibe Code | ProgramBench | Agreement | Week |
|---|---|---|---|---|---|---|---|---|
| 1 |  Anthropic · Proprietary | 1.75 | 2 | 1 | 1 | 3 | Boards agree | – |
| 2 | Anthropic · Proprietary | 2.25 | 1 | 2 | 5 | 1 | Mostly agree | – |
| 3 |  OpenAI · Proprietary | 4.25 | 3 | 3 | 7 | 4 | Mostly agree | – |
| 4 | Anthropic · Proprietary | 4.33 | 5 | – | 6 | 2 | Mostly agree | – |
| 5 |  Google · Proprietary | 5.00 | – | 6 | 2 | 7 | Mostly agree | – |
| 6 | OpenAI · Proprietary | 5.25 | 3 | 4 | 9 | 5 | Mostly agree | – |
| 7 | Anthropic · Proprietary | 7.33 | 8 | – | 4 | 10 | Mostly agree | – |
| 8 | Anthropic · Proprietary | 7.33 | 6 | – | 10 | 6 | Mostly agree | – |
| 9 | Anthropic · Proprietary | 7.67 | – | 12 | 3 | 8 | Boards disagree | – |
| 10 | OpenAI · Proprietary | 9.67 | 7 | – | 11 | 11 | Mostly agree | – |
| 11 |  xAI · Proprietary | 13.00 | 10 | 11 | 13 | 18 | Boards disagree | – |
| 12 |  DeepSeek · Open weights | 13.00 | – | 7 | 12 | 20 | Boards disagree | – |
| 13 |  Meta · Proprietary | 14.67 | 20 | – | 15 | 9 | Boards disagree | – |
| 14 | Meta · Proprietary | 16.00 | – | 8 | 14 | 26 | Boards disagree | – |
| 15 |  Z.ai · Open weights | 16.25 | 9 | 10 | 32 | 14 | Boards disagree | – |
| 16 | OpenAI · Proprietary | 17.00 | 11 | – | 27 | 13 | Boards disagree | – |
| 17 |  Moonshot AI · Open weights | 17.00 | – | 22 | 17 | 12 | Boards disagree | – |
| 18 | Anthropic | 17.33 | 14 | – | 22 | 16 | Boards disagree | – |
| 19 |  Xiaomi · Open weights | 17.67 | – | 15 | 16 | 22 | Boards disagree | – |
| 20 | Google · Proprietary | 21.25 | 17 | 21 | 30 | 17 | Boards disagree | – |
| 20 | OpenAI · Proprietary | 21.25 | 19 | 17 | 24 | 25 | Boards disagree | – |
| 22 | xAI · Proprietary | 22.33 | 16 | – | 36 | 15 | Boards disagree | – |
| 23 | Xiaomi · Open weights | 22.33 | – | 19 | 29 | 19 | Boards disagree | – |
| 24 |  Alibaba · Proprietary | 22.50 | 13 | 9 | 34 | 34 | Boards disagree | – |
| 25 | DeepSeek · Open weights | 22.67 | – | 13 | 23 | 32 | Boards disagree | – |
| 26 | OpenAI · Proprietary | 25.00 | 15 | – | 39 | 21 | Boards disagree | – |
| 27 | Anthropic · Proprietary | 26.67 | 21 | – | 26 | 33 | Boards disagree | – |
| 28 |  Tencent · Open weights | 27.33 | – | 18 | 33 | 31 | Boards disagree | – |
| 29 | OpenAI | 30.00 | 18 | – | 35 | 37 | Boards disagree | – |
| 30 | Google · Proprietary | 34.00 | 23 | – | 44 | 35 | Boards disagree | – |
| 31 | Z.ai · Open weights | 34.50 | 12 | 14 | 73 | 39 | Boards disagree | – |
| 32 | xAI | 35.67 | 21 | – | 46 | 40 | Boards disagree | – |
| 33 |  Thinking Machines · Open weights | 47.67 | – | 27 | 86 | 30 | Boards disagree | – |
| 34 | Thinking Machines · Open weights | 57.33 | – | 28 | 85 | 59 | Boards disagree | – |
The boards behind this ranking
- Terminal-Bench 4.0 by Stanford / Harbor / Laude InstituteFrontier-difficulty tasks in a real terminal. 23 models. Updated Sep 29.
- Code Migration by Vals AIReimplementing working programs in another language. 28 models. Updated Oct 30.
- Vibe Code by Vals AIBuilding web applications from scratch. 115 models. Updated Oct 29.
- ProgramBench by Vals AIRebuilding programs from scratch. 62 models. Updated Oct 29.
81 more models appear on too few of these boards to average fairly, so they are not ranked here.
Sources: Arena leaderboard dataset (CC BY 4.0; we keep each model's best configuration and renumber), Terminal-Bench, Vals AI benchmarks. Re-read every week. How we calculate it. eSEOspace does not run these benchmarks and has not tested these models for this ranking. The order comes from the formula, and no one can pay for a position. eSEOspace is a member of the Claude Partner Network, and Claude is one of the models ranked here.
How to read it
How to read this ranking
Read the average rank first: lower is better. Then look at the Agreement column. A model the boards agree on is a safer bet than one that is first on one board and twentieth on another.
Select a model's name to see its score on each board and the harness used. Use the tabs to switch from the overall list to coding, knowledge work or reliability, and the filters to narrow by lab or to open-weight models.
Other views: Overall. Knowledge work. Reliability. Methodology.
Limits
What this ranking can't tell you
A high average tells you a model did well on these tests. It does not prove it will handle your work, your data or your tools. Run your own trial on real tasks before you commit.
Boards do not cover every model. A model missing from a tough board can look better than one that was tested and scored lower, which is why we show how many boards each model appears on and whether they agree.
Benchmarks can also be gamed. Researchers have shown that agents can sometimes score well by exploiting a test rather than solving it, so treat a small gap between two models as a tie.
These boards often pair a model with one harness. The same model can score differently in Claude Code, Codex, Cursor or OpenHands, so open a row to see which harness produced its result.
FAQ
Common questions
What is the best AI coding agent right now?
Why is Terminal-Bench on this list but not SWE-bench?
Does the harness matter as much as the model?
Next steps
Go deeper
AI Agent vs Chatbot vs Automation: What Is Different
Read the guide →Model vs Agent vs Harness: Why the Same AI Scores Differently
Read the guide →AI Agent Cost Per Task: Why Token Price Misleads
Read the guide →AI Agent Frameworks Compared: Claude SDK, OpenAI, LangGraph
Read the guide →Best AI Agents for Accounting and Bookkeeping: 9 Options
Read the guide →Best AI Customer Support Agents: 9 Options Compared
Read the guide →All AI agent guides
See all guides →
Project Managers who will work with you on your project!
Irina S.hello@eseospace.com
Benjamin G.ben@eseospace.com
David G.david@eseospace.comWork with us
Talk to the team behind your project
Tell us what you need and we’ll match you with the right people.
Book a Discovery Call
Jeanette M.jeanette@eseospace.com
Mark S.mark@eseospace.com
Maryna P.maryna@eseospace.com
Wondering what this costs? Every service has published pricing, and you don't need a discovery call to see it.
View pricingPicking an AI agent for your business?
A benchmark rank tells you which models are strong. It does not tell you which one fits your data, your tools and your risk. Tell us what you want the agent to do and we will give you a straight answer.
Talk to our team
