Do coding agents recommend Mistral web search?
Mistral web search was chosen in 2% of 499 judged AI search sessions, ranking tenth. Measured with Claude Code, Codex, Cursor, Grok Build CLI and Muse Code.
Mistral web search was chosen in 2% of 499 judged AI search sessions, ranking tenth. It was also raised as a candidate in 9 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 Mistral web search. What an agent actually installed.
One thing to read first: every one of those wins came from a single codebase. That is a result about one repository rather than about AI search in general, and the splits below cannot separate the two. Treat them as a description of that repository.
The numbers
| Category | AI search |
| Sessions in the category | 499 |
| Sessions where Mistral web search was chosen | 12 |
| Install share | 2% |
| Rank in category | 10 of 41 |
| Codebases it won in | 1 |
| Raised as a candidate, not chosen | 9 |
| Chosen when considered | 57% |
| Site | mistral.ai |
By agent
With 12 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.
| Agent | Sessions | Chose Mistral web search | Share |
|---|---|---|---|
| Claude Code | 140 | 5 | 4% |
| Codex | 144 | 5 | 3% |
| Cursor | 136 | 1 | 1% |
| Grok Build CLI | 35 | 1 | 3% |
| Muse Code | 44 | 0 | 0% |
By who was asking
Mistral web search performs similarly across the four kinds of buyer, from 0% to 4%. That is unusual: the category leader changed with the persona in 23 of the 29 categories we measured.
| Who is asking | Sessions | Chose Mistral web search | Share |
|---|---|---|---|
| Vibe coder | 82 | 0 | 0% |
| Junior developer | 173 | 7 | 4% |
| Senior engineer | 124 | 0 | 0% |
| Enterprise team | 120 | 5 | 4% |
What Mistral web search was up against
The full ranking in AI search, from the same sessions:
| # | Product | Runs won | Share |
|---|---|---|---|
| 1 | Anthropic web search | 84 | 17% |
| 2 | Brave Search API | 69 | 14% |
| 3 | Exa | 67 | 13% |
| 4 | Tavily | 42 | 8% |
| 5 | OpenAI web search | 27 | 5% |
| 6 | Built in-house (no product adopted) | 24 | 5% |
| 7 | Firecrawl | 23 | 5% |
| 8 | NewsAPI.ai | 23 | 5% |
What this means
Agents almost never raise Mistral web search without choosing it: 9 sessions raised against 12 chosen. When it gets considered, it usually wins. The constraint is how rarely it gets considered at all, which is a presence problem: templates, framework integrations and pages that answer the configuration and production questions agents actually search for.
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 Mistral web search: 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 Mistral web search?
Yes. Mistral web search was chosen in 12 of the 499 judged sessions in AI search, a 2% install share, ranking tenth in its category.
Does Claude Code recommend Mistral web search?
In 5 of the 140 sessions in AI search run with Claude Code, which is 4%.
Do different coding agents treat Mistral web search differently?
Not much. Claude Code, Codex, Cursor, Grok Build CLI and Muse Code chose it at similar rates, between 0% and 4% 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 Mistral web search considered but not chosen?
It was raised as a candidate in 9 sessions without being chosen, and chosen in 12. That is a 57% 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.