From the experiment

Do coding agents recommend Bing grounding?

Bing grounding was chosen in 2% of 499 judged AI search sessions, ranking number 11. Measured with Claude Code, Codex, Cursor, Grok Build CLI and Muse Code.

Published September 23, 2026 Read as Markdown

Bing grounding was chosen in 2% of 499 judged AI search sessions, ranking number 11. It was also raised as a candidate in 26 further sessions without being chosen.

This page reports what happened when Claude Code, Codex, Cursor, Grok Build CLI and Muse Code had to solve a problem in AI search inside a realistic codebase. Not what a chat assistant says about Bing grounding. What an agent actually installed.

The numbers

CategoryAI search
Sessions in the category499
Sessions where Bing grounding was chosen10
Install share2%
Rank in category11 of 41
Codebases it won in2
Raised as a candidate, not chosen26
Chosen when considered28%
Siteazure.microsoft.com

By agent

With 10 wins spread across 5 agents, the rates below are small numbers and a difference between them is not yet a finding. They are here because the direction is worth knowing, not because the gap is established.

AgentSessionsChose Bing groundingShare
Claude Code14000%
Codex14421%
Cursor13654%
Grok Build CLI3513%
Muse Code4425%

By who was asking

Bing grounding performs similarly across the four kinds of buyer, from 0% to 6%. That is unusual: the category leader changed with the persona in 23 of the 29 categories we measured.

Who is askingSessionsChose Bing groundingShare
Vibe coder8200%
Junior developer17300%
Senior engineer12476%
Enterprise team12033%

What Bing grounding was up against

The full ranking in AI search, from the same sessions:

#ProductRuns wonShare
1Anthropic web search8417%
2Brave Search API6914%
3Exa6713%
4Tavily428%
5OpenAI web search275%
6Built in-house (no product adopted)245%
7Firecrawl235%
8NewsAPI.ai235%

What this means

Bing grounding was raised in 26 sessions and chosen in 10. That ratio is balanced enough that the ceiling is presence rather than integration: the product converts reasonably when it is on the table, and it is not on the table often enough.

Where these numbers come from

The 499 sessions in AI search are part of a published set of 11,878, run with real coding agents inside realistic codebases and judged blind. The full method is on one page: how we measured this.

Every AI search run can be replayed on the board.

If you work on Bing grounding: the judge recorded a reason for every session where it was raised and passed over. Those reasons are in the transcripts.

<!-- generated by scripts/write-data-pages.mjs -->

Common questions

Do coding agents recommend Bing grounding?

Yes. Bing grounding was chosen in 10 of the 499 judged sessions in AI search, a 2% install share, ranking number 11 in its category.

Does Claude Code recommend Bing grounding?

In 0 of the 140 sessions in AI search run with Claude Code, which is 0%.

Do different coding agents treat Bing grounding differently?

Not much. Claude Code, Codex, Cursor, Grok Build CLI and Muse Code chose it at similar rates, between 0% and 5% of their runs.

How was this measured?

Real coding agents at pinned versions were run in sandboxes inside 91 realistic codebases and asked to solve real tasks. A simulated project owner approved or questioned each recommendation before any code was written, and a judge from a model family that builds none of the agents read every session blind.

How often is Bing grounding considered but not chosen?

It was raised as a candidate in 26 sessions without being chosen, and chosen in 10. That is a 28% conversion from considered to chosen.

Where this comes from

Armature ran 11,878 judged sessions with Claude Code, Codex, Cursor, Grok Build CLI and Muse Code inside 91 realistic codebases, and published every run. The numbers on this page come from that work.

Read next

All library pages